Methods, devices, equipment and storage media for automatic monitoring of the condition of low-voltage power distribution lines

By using time-scale weighting and multi-scale correlation calculation at the edge, combined with aliasing path judgment threshold, resources are dynamically allocated and closed-loop correction is performed in the cloud, solving the problem of low coverage of low-voltage power distribution line status monitoring and achieving efficient monitoring with full coverage.

CN123122007APending Publication Date: 2026-11-17STATE GRID ZHEJIANG ELECTRIC POWER COMPANY TAIZHOU POWER SUPPLY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611610303.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-10-19
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

Existing technologies for monitoring the condition of low-voltage power distribution lines cannot effectively distinguish the correlation superposition caused by load coupling of multiple branches and fault propagation, resulting in low monitoring coverage. Furthermore, the high-frequency acquisition and uploading of data exceeds the capabilities of edge computing power and communication bandwidth, making it impossible to achieve full coverage monitoring.

Method used

By collecting raw electrical data of low-voltage distribution lines at the edge, performing time-scale weighting and multi-scale correlation calculations, and combining the pre-stored aliasing path judgment threshold, the aliasing intensity and effective aliasing path number of each branch are quantified. The sampling frequency, calculation depth and transmission mode are dynamically allocated to generate monitoring priorities. The aliasing path judgment threshold is then updated in the cloud in association with real abnormal event labels to form a closed-loop correction.

Benefits of technology

Under the constraints of limited edge computing power and communication bandwidth, effective monitoring of all branches was achieved, improving the monitoring coverage of low-voltage distribution line status, avoiding misjudgments, and adapting to changes in transformer area load and topology.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123122007A_ABST
    Figure CN123122007A_ABST
Patent Text Reader

Abstract

This application discloses an automatic monitoring method, device, equipment, and storage medium for the status of low-voltage power distribution lines, relating to the field of power distribution line monitoring technology. The method collects raw electrical data from each branch, performs time-scale weighted and multi-scale correlation calculations, and combines this with pre-stored thresholds to obtain aliasing intensity and the number of effective aliasing paths. Based on this, it jointly allocates sampling frequency, computation depth, and transmission mode to generate monitoring priorities. Monitoring data is then collected and uploaded to the cloud. The cloud associates the monitoring data with real abnormal event tags, updates the aliasing path judgment threshold, and distributes it. The edge device receives the updated threshold for subsequent branch status monitoring. In other words, through a cycle of aliasing quantification, joint resource allocation, and closed-loop correction of real events, all branches can be effectively monitored under conditions of limited edge computing power and communication bandwidth, thereby improving the monitoring coverage of low-voltage power distribution line status.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This application relates to the field of power distribution line monitoring technology, and in particular to methods, devices, equipment and storage media for automatic monitoring of the status of low-voltage power distribution lines. Background Technology

[0002] Low-voltage distribution substations are the end-point power supply units of a power system. A single feeder has multiple user branches under its jurisdiction, and the electrical status parameters of each branch can reflect the line's operating conditions in real time, which can be used for anomaly identification in low-voltage distribution substations.

[0003] Currently, low-voltage power distribution line condition monitoring typically uses a fixed sampling frequency to collect electrical data from each branch, identifies anomalies based on single-branch thresholds, and uploads the collected data to the cloud for processing. However, when performing correlation analysis, it is impossible to quantify the superposition of correlations caused by load coupling and fault propagation across multiple branches. When an anomaly occurs in a branch, multiple branches coupled with it will produce similar responses, and the fixed threshold cannot distinguish between the anomaly source, the disturbed branch, and normal load fluctuations. To differentiate these responses, it is necessary to increase the sampling frequency and upload complete data, but collecting and uploading data from all branches in this way would exceed the capacity of edge computing power and communication bandwidth, thus preventing all branches from being effectively monitored and resulting in low monitoring coverage of low-voltage power distribution line conditions.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide an automatic monitoring method, device, equipment, and storage medium for the status of low-voltage power distribution lines, aiming to solve the technical problem that the monitoring coverage of low-voltage power distribution lines is low because not all branches can be effectively monitored.

[0006] To achieve the above objectives, this application proposes an automatic monitoring method for the condition of low-voltage power distribution lines, applied at the edge end. The method includes: Collect raw electrical data for each branch of the low-voltage power distribution line; After performing time-scale weighting and multi-scale correlation calculation on the original electrical data, and combining it with the pre-stored aliasing path judgment threshold, the aliasing intensity and effective aliasing path number of each branch correlation are obtained. Based on the aliasing intensity and the number of effective aliasing paths, the sampling frequency, computation depth and transmission mode of each branch are jointly allocated to generate the monitoring priority of each branch. The monitoring data is collected according to the sampling frequency and the calculation depth, and uploaded to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results. Receive the updated aliasing path judgment threshold from the cloud and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0007] In one embodiment, the step of performing time-scale weighted and multi-scale correlation calculations on the original electrical data, and then combining this with a pre-stored aliasing path judgment threshold to obtain the aliasing intensity and effective aliasing path number of each branch correlation includes: Based on the original electrical data, a time series is generated according to a unified time scale, and the multi-scale correlation between each branch is calculated. Based on the multi-scale correlation, preset constraint information and pre-stored aliasing path judgment threshold, the comprehensive aliasing relationship of each branch is determined. The constraint information includes preset topological constraints, preset abnormal window identifiers and preset data credibility. Based on the comprehensive aliasing relationship and the aliasing path judgment threshold, the aliasing intensity and the number of effective aliasing paths of each branch correlation are obtained.

[0008] In one embodiment, the step of obtaining the aliasing intensity and the number of effective aliasing paths of each branch correlation based on the comprehensive aliasing relationship and the aliasing path judgment threshold includes: Based on the comprehensive aliasing relationship, within a preset topological neighborhood, each branch is weighted according to a preset weighting coefficient to obtain the weighted aliasing amount of each branch. The weighting coefficient is determined based on a preset topological distance and a preset branch capacity. When the weighted aliasing amount satisfies the preset aliasing interval rules, the aliasing interval of each branch is determined. The aliasing interval rules include a start threshold, an exit threshold, and a minimum maintenance duration. Within the aliasing interval, the number of branches that meet the aliasing condition in each branch is counted. The aliasing condition is that the comprehensive aliasing relationship in the topological neighborhood is greater than or equal to the aliasing path judgment threshold. The weighted aliasing amount is used as the aliasing intensity of each branch correlation, and the number of branches is used as the number of effective aliasing paths.

[0009] In one embodiment, the step of calculating the multi-scale correlation between branches based on the original electrical data, generating a time series according to a unified time scale, includes: The original electrical data is divided into time intervals according to a unified time scale, and the original electrical data falling into the same time interval are weighted and aggregated according to the sampling interval of each sampling time to obtain the time series values ​​of each branch at the three time scales of seconds, minutes and hours. Calculate the temporal variation of each branch based on the temporal values ​​of adjacent time intervals; Based on the time series value, the preset importance coefficient of the electrical state quantity and the preset data reliability weight, calculate the same-scale amplitude correlation coefficient between each branch, and based on the time series change, the importance coefficient and the data reliability weight, calculate the same-scale trend correlation coefficient between each branch. Based on the temporal changes of each branch at different time scales, cross-correlation calculations are performed on the temporal changes to obtain cross-correlation values ​​that vary with relative time delay, and the maximum value among the cross-correlation values ​​is taken as the cross-scale correlation strength. The multi-scale correlation between branches is obtained based on the same-scale amplitude correlation coefficient, the same-scale trend correlation coefficient, and the cross-scale correlation strength.

[0010] Furthermore, to achieve the above objectives, this application also proposes an automatic monitoring method for the status of low-voltage power distribution lines, applied in a cloud-based manner, the method comprising: The edge terminal receives monitoring data uploaded according to monitoring priority and transmission mode. The monitoring priority is generated by the edge terminal based on the aliasing intensity and the number of effective aliasing paths, and the sampling frequency, calculation depth and transmission mode of each branch are jointly allocated. The aliasing intensity and the number of effective aliasing paths are obtained by the edge terminal by performing time-scale weighting and multi-scale correlation calculation on the original electrical data of each branch in the low-voltage distribution line, and combining it with the pre-stored aliasing path judgment threshold. The monitoring data is collected by the edge terminal according to the sampling frequency and the calculation depth. The monitoring data is correlated with the acquired real abnormal event tags to obtain the correlation results; The aliasing path judgment threshold is updated based on the association result, and the updated aliasing path judgment threshold is sent to the edge terminal so that the edge terminal can use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0011] In one embodiment, the step of updating the aliasing path determination threshold based on the association result includes: Based on the correlation results, determine the effectiveness of the sampling adjustment and the error in judging the aliasing path; Under the preset coverage lower limit constraint, the current aliasing path judgment threshold is updated according to the sampling adjustment validity and the aliasing path judgment error to obtain the updated aliasing path judgment threshold.

[0012] In one embodiment, the aliasing path determination error includes the aliasing path false inclusion rate and the aliasing path missed inclusion rate; Under a preset coverage lower limit constraint, the step of updating the current aliasing path judgment threshold based on the sampling adjustment effectiveness and the aliasing path judgment error to obtain the updated aliasing path judgment threshold includes: Under the preset coverage lower limit constraint, if the sampling adjustment validity meets the preset validity condition, then the branch pairs that actually have abnormal associations are determined according to the association results; The aliasing path under-inclusion rate is obtained by calculating the proportion of branch pairs whose overall aliasing relationship is lower than the current aliasing path judgment threshold. If the false inclusion rate of the aliasing path is higher than the preset false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the preset false omission rate threshold, then the current aliasing path judgment threshold is increased to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is lowered to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the false omission rate threshold, then the current aliasing path judgment threshold remains unchanged, and the updated aliasing path judgment threshold is obtained. If the false inclusion rate of the aliasing path is higher than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is updated according to the recalibrated basic parameters to obtain the updated aliasing path judgment threshold.

[0013] Furthermore, to achieve the above objectives, this application also proposes an automatic monitoring device for the condition of low-voltage power distribution lines, the automatic monitoring device for the condition of low-voltage power distribution lines comprising: The data acquisition module is used to collect raw electrical data from each branch of the low-voltage power distribution line. The calculation module is used to perform time-scale weighting and multi-scale correlation calculation on the original electrical data, and then combine it with the pre-stored aliasing path judgment threshold to obtain the aliasing intensity and effective aliasing path number of each branch correlation. The sorting module is used to jointly allocate the sampling frequency, computation depth and transmission mode of each branch according to the aliasing intensity and the number of effective aliasing paths, and generate the monitoring priority of each branch. The monitoring module is used to collect monitoring data according to the sampling frequency and the calculation depth, and upload the monitoring data to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results; The update module is used to receive the updated aliasing path judgment threshold from the cloud and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0014] In addition, to achieve the above objectives, this application also proposes an automatic monitoring device for the status of low-voltage power distribution lines, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the automatic monitoring method for the status of low-voltage power distribution lines as described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the automatic monitoring method for the status of low-voltage power distribution lines as described above.

[0016] One or more technical solutions proposed in this application have at least the following technical effects: By collecting raw electrical data from each branch of a low-voltage distribution line and performing time-scale weighting and multi-scale correlation calculations on the raw electrical data, data from different sampling times can be unified to the same physical time base. The correlation superposition caused by load coupling and fault propagation in multiple branches can be quantified. Combined with preset aliasing path judgment values, the aliasing intensity and effective aliasing path number of each branch can be obtained, thus distinguishing abnormal sources, disturbed branches, and normal load fluctuations, avoiding misjudgments caused by fixed thresholds for single branches. Furthermore, based on the aliasing intensity and the effective aliasing path number, the sampling frequency, calculation depth, and transmission mode of each branch are jointly allocated to generate monitoring priorities for each branch. The system prioritizes limited edge computing power and communication bandwidth towards branches with high aliasing and high anomaly risk, avoiding the need for high-frequency data collection and uploading of complete data from all branches. Monitoring data is then collected based on sampling frequency and computational depth, and uploaded to the cloud according to monitoring priority and transmission mode. The cloud then associates the monitoring data with real anomaly event tags and updates the aliasing path judgment threshold based on the association results. Independent real event tags can be used for closed-loop correction of the threshold, ensuring it adapts to area load and topology changes. Finally, the updated aliasing path judgment threshold is received from the cloud and used for subsequent branch status monitoring. In other words, through a cycle of aliasing quantification, joint resource allocation, and real event closed-loop correction, all branches can be effectively monitored under limited edge computing power and communication bandwidth, thereby improving the monitoring coverage of low-voltage distribution lines. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating an embodiment of the automatic monitoring method for low-voltage power distribution lines in this application. Figure 2 This is a flowchart illustrating the automatic monitoring method for the status of low-voltage power distribution lines in this application. Figure 3 This is a flowchart illustrating Embodiment 2 of the automatic monitoring method for low-voltage power distribution lines in this application. Figure 4 This is a flowchart illustrating Embodiment 3 of the automatic monitoring method for low-voltage power distribution lines in this application. Figure 5 This is a schematic diagram of the module structure of the automatic monitoring device for low-voltage power distribution line status according to an embodiment of this application; Figure 6 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the automatic monitoring method for the status of low-voltage power distribution lines in this application embodiment.

[0020] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions, a control device for low-voltage power distribution lines (the control device includes the edge end and cloud end of the low-voltage power distribution line), etc. The following description uses a control device as an example to illustrate this embodiment and the subsequent embodiments.

[0024] Based on this, embodiments of this application provide an automatic monitoring method for the status of low-voltage power distribution lines, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the automatic monitoring method for low-voltage power distribution lines according to this application.

[0025] In this embodiment, the automatic monitoring method for the status of low-voltage power distribution lines is applied at the edge end, and the method includes steps S10~S50: Step S10: Collect the original electrical data of each branch in the low-voltage power distribution line; It should be noted that the edge terminal is a smart terminal deployed on the side of the distribution transformer or in the branch box of the line. The raw electrical data includes, but is not limited to, real-time electrical quantities reflecting the operating status of the line, such as voltage, current, power factor, and harmonic content of each branch. Low-voltage distribution lines are terminal distribution networks with a rated voltage of 380V or 220V; branches are branch lines that branch off from the main line and supply power to users.

[0026] Understandably, by directly collecting the raw electrical data of each branch at the edge, the most accurate line operation information can be obtained nearby, avoiding the risks of delay and packet loss caused by long-distance data transmission. It can also provide a timely and reliable data foundation for subsequent status monitoring, ensuring the real-time performance and accuracy of the data source.

[0027] In practical implementation, the intelligent monitoring terminal at the edge can continuously collect the instantaneous values ​​of three-phase voltage and three-phase current of each branch at a preset reference sampling frequency, such as 50 times per second, using built-in current transformers and voltage transformers. The collected raw electrical data is temporarily stored in the local cache at the edge, and precise timestamps can be added to the collected raw electrical data for subsequent time-stamp alignment and analysis.

[0028] Step S20: After performing time-scale weighting and multi-scale correlation calculation on the original electrical data, the aliasing intensity and number of effective aliasing paths of each branch are obtained by combining the pre-stored aliasing path judgment threshold. It should be noted that time-stamped weighting assigns different weights to data collected at different times based on the timestamp and sampling interval, to eliminate the impact of clock asynchrony or uneven sampling intervals. Multi-scale correlation calculation analyzes the degree of correlation between electrical data of each branch at multiple time scales, such as second-level, grade-level, and hour-level. The aliasing path judgment threshold is determined by the cloud based on monitoring data from the previous period and sent to the edge to determine whether there is significant electrical coupling or fault correlation between two branches. Aliasing intensity is an indicator that quantifies the comprehensive correlation between a branch and other surrounding branches; a higher value indicates a stronger correlation. The effective aliasing path count is the number of other branches that are strongly correlated with this branch in the current state.

[0029] Understandably, by performing time-scale weighting and multi-scale correlation calculations on the raw electrical data, the problems of asynchronous field clocks and inconsistent sampling intervals can be overcome, and the complex electrical coupling relationships between branches can be revealed from different time dimensions.

[0030] Understandably, by combining the pre-stored aliasing path judgment threshold, it is possible to accurately identify which branches have effective aliasing relationships and quantify the strength and range of the relationship, thereby extracting high-value feature information that characterizes the topological association status of the lines from massive amounts of raw data.

[0031] In the specific implementation, the edge device first performs time-stamping standardization on the collected raw electrical data. For example, the data from all sampling points are interpolated and resampled according to a unified UTC time coordinate. Subsequently, the Pearson correlation coefficient of the voltage and current waveforms of each branch is calculated on a second-level scale; the consistency of the active power change trend of each branch is calculated on a graded scale; and the synchronicity of the load rate of each branch is calculated on an hour-level scale. The multi-scale calculation results are weighted and fused, and compared with a preset aliasing path judgment threshold. When the multi-scale correlation of two branches continuously exceeds the threshold, it is considered that there is a valid aliasing path between them. By traversing all branch pairs, the aliasing intensity of each branch and the number of valid aliasing paths can be statistically determined.

[0032] Step S30: Based on the aliasing intensity and the number of effective aliasing paths, jointly allocate the sampling frequency, computation depth and transmission mode of each branch to generate the monitoring priority of each branch; It should be noted that sampling frequency is the time interval at which the edge device collects data from a specific branch. Computation depth refers to the complexity of processing the collected data, such as calculating only the effective values ​​or performing high-order harmonic analysis. Transmission mode is the strategy for uploading data from the edge device to the cloud, including real-time upload, timed batch upload, or upload only when an anomaly is detected. Monitoring priority indicates the degree of attention each branch needs to receive in the current network state.

[0033] Understandably, branches with high aliasing intensity and a large number of effective aliasing paths indicate that these branches occupy critical coupling positions in the network. A failure in such a branch would have a significant impact on low-voltage distribution lines. Therefore, these branches can be allocated higher sampling frequencies, deeper computational dimensions, and more real-time transmission modes, i.e., given the highest monitoring priority. For isolated or stable branches, resource investment can be reduced. This dynamic and differentiated resource allocation strategy can maximize the monitoring efficiency of key nodes across the entire network with limited edge computing power and communication bandwidth.

[0034] In practical implementation, the edge device can have a built-in resource allocation decision engine. This engine receives aliasing intensity and the number of effective aliasing paths as input. For example, for branches with aliasing intensity greater than 0.8 and the number of effective aliasing paths greater than 3, their monitoring priority is set to the highest level, A, and they are allocated a sampling frequency of 100Hz, subjected to deep calculation of FFT spectrum analysis, and transmitted in real-time. For branches with aliasing intensity less than 0.3 and the number of effective aliasing paths is 0, they are set to the lowest level, C, allocated only a sampling frequency of 1Hz, their fundamental RMS value is calculated, and they are uploaded in batches once per hour.

[0035] Step S40: Collect monitoring data according to the sampling frequency and the calculation depth, and upload the monitoring data to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results; It should be noted that the monitoring data is obtained after processing according to the newly allocated sampling frequency and computational depth. The actual anomaly event labels are confirmed and entered into the system by on-site maintenance personnel during inspections or troubleshooting, specifying the actual fault type and time point, such as: phase A ground short circuit, overload, etc.

[0036] Understandably, by collecting and processing data according to dynamically allocated sampling frequencies and computation depths, edge devices can focus resources and efficiently acquire the most critical information reflecting the line status. Then, by uploading data to the cloud according to priority and transmission mode, the real-time nature of critical data and low overhead for non-critical data can be guaranteed.

[0037] Understandably, the cloud performs correlation analysis between uploaded monitoring data and actual anomaly event tags, and then updates the aliasing path judgment threshold based on the correlation results to form an automatic monitoring closed loop. This closed loop process allows for an objective assessment of the accuracy of the current aliasing path judgment threshold. For example, if some branches judged as non-aliased actually experience associated faults, or if branches judged as aliased do not simultaneously exhibit anomalies, it indicates that the aliasing path judgment threshold needs adjustment. In other words, the cloud can adaptively update the aliasing path judgment threshold based on this correlation analysis and distribute the updated threshold to the edge, thereby continuously optimizing the accuracy of the monitoring model.

[0038] Step S50: Receive the updated aliasing path judgment threshold sent from the cloud, and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0039] It should be noted that the updated aliasing path judgment threshold is a new judgment standard optimized by the cloud after learning historical data and real event labels.

[0040] Understandably, by receiving and using the cloud-optimized aliasing path judgment threshold at the edge, the control equipment of low-voltage power distribution lines can achieve self-adjustment, enabling the control equipment to have the ability to learn and continuously evolve. As the operating time increases, it can more accurately identify the real fault-related paths, effectively reducing the false inclusion rate and the missed inclusion rate, thereby improving the full coverage and accuracy of automatic monitoring of the status of low-voltage power distribution lines.

[0041] In its implementation, the edge device checks for new configuration files from the cloud during each communication interaction. Upon receiving an updated aliasing path assessment threshold, the edge device stores this threshold in non-volatile memory, replacing the old threshold. During the next multi-scale correlation calculation and aliasing path determination, the edge device automatically adopts this updated threshold. For example, if the original threshold was 0.6, and the cloud updates it to 0.65, the edge device will use 0.65 to determine if a valid aliasing path exists between branches, thereby changing subsequent aliasing intensity calculations, resource allocation, and monitoring behavior, forming a virtuous cycle of continuous optimization.

[0042] In the specific implementation, refer to Figure 2The edge end first collects raw electrical sampling data for all branches of the low-voltage feeder; then, it performs three-level time-scale weighted aggregation on the raw electrical sampling data to construct a unified physical time series standard. That is, the edge end divides the raw electrical data into time intervals according to a unified time scale, and performs weighted aggregation on data falling into the same time interval according to the sampling interval to obtain the time series values ​​of each branch at the second, minute, and hour time scales, thereby eliminating time series deviations. Based on the time series values, multi-scale branch correlation quantification is performed. That is, the time series change is calculated based on the time series values ​​of adjacent time intervals, and combined with the preset electrical state quantity importance coefficient and data reliability weight, the same-scale amplitude correlation coefficient and same-scale trend correlation coefficient between each branch are calculated, and cross-correlation is performed on different time series changes. The cross-scale correlation strength (correlation quantification calculation result) is calculated. Based on the correlation quantification calculation result, robust anomaly continuous triggering is executed to solve for aliasing strength and the number of effective paths. That is, the comprehensive aliasing relationship is determined by combining preset topological constraints, anomaly window identifiers, and data credibility information. Weighted aliasing is obtained by weighting the aliasing amount within the topological neighborhood according to weighting coefficients. When the weighted aliasing amount meets the aliasing interval rules, the aliasing interval is determined. The number of branches with a comprehensive aliasing relationship greater than or equal to the aliasing path judgment threshold is counted, thereby obtaining the aliasing strength and the number of effective paths. Based on the solved aliasing strength and the number of effective paths, joint resource optimization scheduling of sensing, transmission, and computing is executed. That is, the edge end jointly allocates the sampling frequency of each branch and calculates the aliasing strength and the number of effective paths according to the aliasing strength and the number of effective paths. The system generates monitoring priorities for each branch based on depth and transmission mode. It then uploads full-coverage tiered data (monitoring data), meaning the edge end collects monitoring data according to the allocated sampling frequency and computational depth, and uploads it to the cloud according to monitoring priority and transmission mode. Furthermore, it calculates the overall effective coverage, summarizing and analyzing the monitoring data from each branch to quantify the current effective monitoring coverage of the low-voltage distribution lines. Additionally, after receiving the monitoring data, the cloud performs real work order labeling and calculates the comprehensive sampling utility. This involves associating monitoring data with real abnormal event labels and calculating the comprehensive utility of the current sampling strategy based on this association. Finally, it determines whether the comprehensive utility improvement meets the target and the coverage requirement. The cloud-based system assesses whether the sampling effectiveness meets the verification conditions based on the correlation results (improvement compliance and ensuring that the effective monitoring coverage of the entire region meets the preset lower limit). If the verification conditions are not met, the system performs statistical analysis of the false inclusion / missed inclusion rate and adaptively updates the aliasing path threshold. In other words, the cloud-based system quantifies the false inclusion rate and the missed inclusion rate to adaptively correct the aliasing path judgment threshold, and iteratively sends the updated threshold back to the edge end. The edge end then re-executes the sensor-computer joint resource optimization scheduling based on the updated threshold to achieve closed-loop correction. If the verification conditions are met, the system outputs branch monitoring data and the overall coverage index, ultimately achieving full coverage of automatic monitoring of the low-voltage distribution line status, and the process ends.

[0043] This embodiment provides an automatic monitoring method for the status of low-voltage distribution lines. By collecting raw electrical data from each branch of the low-voltage distribution line and performing time-scale weighting and multi-scale correlation calculations on the raw electrical data, data from different sampling times can be unified to the same physical time reference. The method quantifies the correlation superposition caused by load coupling and fault propagation in multiple branches. Combined with a preset aliasing path judgment value, the aliasing intensity and effective aliasing path number of each branch are obtained, thus distinguishing abnormal sources, disturbed branches, and normal load fluctuations, avoiding misjudgments caused by fixed thresholds for single branches. Furthermore, the sampling frequency, calculation depth, and transmission mode of each branch are jointly allocated based on the aliasing intensity and the effective aliasing path number. The system generates monitoring priorities for each branch, allocating limited edge computing power and communication bandwidth to branches with high aliasing and high anomaly risk. This avoids collecting and uploading complete data from all branches at high frequencies. Monitoring data is then collected based on sampling frequency and computational depth, and uploaded to the cloud according to monitoring priority and transmission mode. The cloud then associates the monitoring data with real anomaly event tags and updates the aliasing path judgment threshold based on the association results. Independent real event tags can be used to perform closed-loop correction on the threshold, making the threshold adaptable to the load and topology changes of the distribution area. Finally, the updated aliasing path judgment threshold is received from the cloud and used for subsequent branch status monitoring. In other words, through the cycle of aliasing quantification, joint resource allocation, and real event closed-loop correction, all branches can be effectively monitored under the condition of limited edge computing power and communication bandwidth, thereby improving the monitoring coverage of low-voltage distribution line status.

[0044] Based on the first embodiment of this application, in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 Step S20 also includes steps S21 to S23: Step S21: Based on the original electrical data, generate a time series according to a unified time scale, and calculate the multi-scale correlation between each branch. Step S22: Based on the multi-scale correlation, preset constraint information and pre-stored aliasing path judgment threshold, determine the comprehensive aliasing relationship of each branch. The constraint information includes preset topological constraints, preset abnormal window identifiers and preset data credibility. Step S23: Based on the comprehensive aliasing relationship and the aliasing path judgment threshold, obtain the aliasing intensity and the number of effective aliasing paths of each branch correlation.

[0045] It should be noted that a unified timescale means aligning all branch data to a common, precise time reference, such as GPS or BeiDou satellite timing. Preset constraint information serves as auxiliary conditions to help determine aliasing relationships. Among these, preset topology constraints are known physical connections of power distribution lines, such as several branches belonging to the same transformer. Preset anomaly window indicators are known planned operations or disturbances occurring within a specific time period, such as capacitor switching. Preset data reliability is an assessment of data quality, such as the packet loss rate due to communication interference.

[0046] Understandably, by generating time series according to a unified time scale and calculating multi-scale correlations, the timing deviations caused by asynchronous clocks or inconsistent sampling intervals of the acquisition devices in each branch are eliminated, so that subsequent correlation calculations are based on a precise time reference, thereby ensuring the accuracy of the correlation results.

[0047] Understandably, by introducing topological constraints on the basis of time uniformity, high correlations between electrically unconnected branches caused by accidental factors can be excluded, avoiding misjudging non-associated branches as having aliasing relationships. Introducing anomaly window markers can mark data within known planned operation or disturbance periods, reducing the weight of correlation within those periods, thus avoiding misjudging normal operational fluctuations as fault associations. Introducing data reliability can assign lower weights to poor-quality data caused by communication interference or sensor failures, thereby reducing the interference of unreliable data on the judgment results. Through the combined effect of multi-dimensional constraint information, the final determined comprehensive aliasing relationship can more realistically reflect the inherent electrical coupling state between branches. Therefore, the aliasing intensity and the number of effective aliasing paths obtained by comparing this comprehensive aliasing relationship with the aliasing path judgment threshold have higher reliability and robustness, effectively improving the accuracy of condition monitoring.

[0048] In the specific implementation, firstly, the edge device aligns the timestamped sampled data of each branch to the same UTC (Coordinated Universal Time) time axis, eliminating clock skew through interpolation or resampling. Then, the original electrical data is time-scaled and weighted according to the standardized time-series value formula to obtain the standardized time-series values ​​of each branch at the second, minute, and hour time scales. The time-series variation of each branch is then calculated according to the time-series fluctuation variation formula. Next, based on the time-series values ​​and time-series variation, the same-scale amplitude comprehensive correlation coefficient is calculated according to the amplitude comprehensive correlation coefficient formula, the same-scale trend comprehensive correlation coefficient is calculated according to the trend comprehensive correlation coefficient formula, and the cross-scale time-delay cross-correlation is calculated according to the cross-scale time-delay cross-correlation formula to obtain the cross-scale correlation strength. Combining these three types of correlation coefficients, the multi-scale correlation between each branch is obtained.

[0049] Specifically, the formula for the standardized time series value is: ; in, Let be the standardized time series value of the i-th branch, the q-th electrical quantity, at the s-th time scale, and the k-th time interval; For the k-th fixed physical time interval at the s-th time scale; This is the original sampled value of the nth original sampling point in the i-th branch and the q-th type of electrical quantity; The time interval between adjacent sampling; Use extremely small positive numbers to prevent the denominator from being 0.

[0050] The formula for the change in time series fluctuations is: ; in, Let be the time-series change of the i-th branch and the q-th electrical quantity at the s-th time scale, used for trend and cross-scale correlation calculations.

[0051] The formula for the comprehensive correlation coefficient of amplitude is: ; in, Let be the comprehensive correlation coefficient of the amplitudes of the i-th branch and the j-th branch at the s-th time scale; Let be the confidence weight of the i-th branch, the j-th branch, and the q-th electrical quantity at the s-th time scale; The importance coefficient for the qth electrical quantity is fixed. Here, Pearson correlation operator is used; Q is the set of all electrical state variables. Let be the time-series fluctuation increment of the q-th type of electrical quantity of branch j at scale s.

[0052] The formula for the trend correlation coefficient is: ; in, Let be the combined trend correlation coefficient between the i-th branch and the j-th branch at the s-th time scale.

[0053] The formula for cross-scale time delay cross-correlation is: ; in, For time-normalized operators; Let be the cross-scale cross-correlation function of the i-th branch at the s-th time scale and the j-th branch at the r-th time scale; ; For time-delay indexes; For the optimal correlation time delay offset, the superscript Mark the optimal solution; This represents the cross-scale correlation strength.

[0054] Secondly, the edge device reads preset constraint information, including preset topology constraints, preset anomaly window identifiers, and preset data reliability. Topology constraints are derived from the physical wiring diagram of the power distribution lines, recording the connection relationships between branches; anomaly window identifiers are planned operation schedules maintained in the cloud or locally; and data reliability is a quality score calculated in real time based on communication packet loss rate, data verification results, etc. The edge device inputs this constraint information along with multi-scale correlation into the aliasing relationship determination module, and calculates the comprehensive aliasing relationship of each branch pair according to the comprehensive aliasing relationship formula. For example, for a pair of branches, if their multi-scale correlation is high, but the topology constraints show that they are not electrically connected, then a topology correlation correction coefficient K is used. top Remove the highly correlated element; if the highly correlated element happens to occur within the abnormal window, then synchronize the abnormal window flag. Reduce the weight of that branch; if the data reliability of one of the branches is low, then adjust the reliability weight. and Reduce the confidence level of the correlation between the two branches.

[0055] Specifically, the formula for the comprehensive aliasing relationship is: ; in, The aliasing relationship between the i-th branch and the j-th branch at time t; , , These are the weighting coefficients for the three types of correlation strength.

[0056] Finally, the edge will combine the aliasing relationship with the pre-stored aliasing path to determine the threshold. The comparison is performed. For each branch, within its topological neighborhood, the weighted aliasing amount is calculated according to the correlation aliasing intensity formula to obtain the aliasing intensity of that branch. Simultaneously, according to the formula for the number of effective aliasing paths, the overall aliasing relationship within the topological neighborhood is greater than or equal to... The number of branches is used to obtain the number of effective aliasing paths. Specifically, the aliasing intensity is the sum of the weighted composite aliasing relationships of all neighboring branches, and the effective aliasing path number is the number of branch pairs that exceed the threshold.

[0057] Specifically, the formula for the correlation aliasing strength is: ; in, The value is [0,1]; N i Let i be the set of branches in the topological neighborhood of branch i; The weighting coefficient between the i-th branch and the j-th branch is set based on topological distance and capacity. Interval extraction rules: Set... , And lasting no less than Entering high aliasing; below Exit after a specified duration to avoid frequent switching. The threshold for initiating high aliasing regions; The threshold for exiting high aliasing regions; This is the minimum duration for maintaining a high aliasing state.

[0058] The formula for the number of effective aliasing paths is: ; in, This is an indicator function; it outputs 1 if the condition is true, and 0 otherwise. Threshold for determining aliasing paths.

[0059] Furthermore, step S23 also includes: Based on the comprehensive aliasing relationship, within a preset topological neighborhood, each branch is weighted according to a preset weighting coefficient to obtain the weighted aliasing amount of each branch. The weighting coefficient is determined based on a preset topological distance and a preset branch capacity. When the weighted aliasing amount satisfies the preset aliasing interval rules, the aliasing interval of each branch is determined. The aliasing interval rules include a start threshold, an exit threshold, and a minimum maintenance duration. Within the aliasing interval, the number of branches that meet the aliasing condition in each branch is counted. The aliasing condition is that the comprehensive aliasing relationship in the topological neighborhood is greater than or equal to the aliasing path judgment threshold. The weighted aliasing amount is used as the aliasing intensity of each branch correlation, and the number of branches is used as the number of effective aliasing paths.

[0060] It should be noted that the topological neighborhood is a local area defined by electrical distance centered on a certain branch, for example, all outgoing lines on the same busbar. The weighting coefficient is a weight value calculated based on the topological distance and branch capacity; the closer the branch is and the larger its capacity, the higher its weight. The aliasing interval is the duration during which a branch enters a strongly correlated state. The start and end thresholds in the aliasing interval rules are used to prevent frequent state transitions, and the minimum duration is used to eliminate brief, pulse-like interference.

[0061] It is understandable that since the weighting coefficients are determined based on topological distance and branch capacity, the closer the branch is and the greater its capacity, the greater its influence on the central branch. Therefore, the weighted aliasing amount can more accurately reflect the actual contribution of each branch in the neighborhood to the central branch, thus avoiding the distortion caused by equal weighted averaging.

[0062] Understandably, the hysteresis interval between the start threshold and the exit threshold can prevent frequent entry and exit from the aliasing state due to noise or short-term fluctuations, while the minimum maintenance duration can eliminate pulse interference. Therefore, only strongly correlated states that continuously and stably exceed the threshold will be identified as valid aliasing intervals, thereby significantly reducing the probability of misjudgment.

[0063] Understandably, since spurious correlations and transient interferences have been eliminated from the aliasing interval, the number of branches counted can accurately reflect the scale of other branches that have a stable and strong correlation with the central branch.

[0064] Furthermore, step S21 also includes: The original electrical data is divided into time intervals according to a unified time scale, and the original electrical data falling into the same time interval are weighted and aggregated according to the sampling interval of each sampling time to obtain the time series values ​​of each branch at the three time scales of seconds, minutes and hours. Calculate the temporal variation of each branch based on the temporal values ​​of adjacent time intervals; Based on the time series value, the preset importance coefficient of the electrical state quantity and the preset data reliability weight, calculate the same-scale amplitude correlation coefficient between each branch, and based on the time series change, the importance coefficient and the data reliability weight, calculate the same-scale trend correlation coefficient between each branch. Based on the temporal changes of each branch at different time scales, cross-correlation calculations are performed on the temporal changes to obtain cross-correlation values ​​that vary with relative time delay, and the maximum value among the cross-correlation values ​​is taken as the cross-scale correlation strength. The multi-scale correlation between branches is obtained based on the same-scale amplitude correlation coefficient, the same-scale trend correlation coefficient, and the cross-scale correlation strength.

[0065] It should be noted that a time interval divides a continuous time axis into consecutive, fixed-length time periods. Weighted aggregation involves averaging data within a time interval, assigning different weights to each sampling point based on its distance from the interval's center, to smooth the data. Importance coefficients reflect the varying importance of different electrical quantities, such as voltage, current, and power, in determining line status. Data reliability weights are used to reduce the impact of low-quality data on calculation results. Same-scale amplitude correlation coefficients measure the similarity in the magnitude of electrical quantities between two branches at the same time scale. Same-scale trend correlation coefficients measure the synchronicity of the direction of change in electrical quantities between two branches. Cross-scale correlation strength measures whether changes in one branch can predict changes in another branch at different time scales.

[0066] Understandably, by weighting and aggregating raw data across three typical time scales—seconds, minutes, and hours—we can effectively extract electrical characteristics at different time granularities, while also considering the perception of both rapid transient processes and slow trend changes. Simultaneously calculating amplitude and trend correlations allows for a comprehensive characterization of the inter-branch relationships from both static numerical and dynamic perspectives. Introducing cross-scale correlation strength can capture causal or predictive relationships between different time scales; for example, hourly load changes may lead to minute-level voltage fluctuations. The organic combination of these three correlation coefficients can constitute a three-dimensional, multi-dimensional similarity measurement system.

[0067] Based on the first and second embodiments of this application, the same or similar content as the above embodiments in the third embodiment of this application can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 4 The automatic monitoring method for the status of low-voltage power distribution lines can also be applied to the cloud. The method includes steps S1 to S3: Step S1: Receive monitoring data uploaded by the edge terminal according to monitoring priority and transmission mode. The monitoring priority is generated by the edge terminal based on the aliasing intensity and the number of effective aliasing paths, and jointly allocates the sampling frequency, calculation depth and transmission mode of each branch. The aliasing intensity and the number of effective aliasing paths are obtained by the edge terminal by performing time-scale weighting and multi-scale correlation calculation on the original electrical data of each branch in the collected low-voltage distribution line, and then combining it with the pre-stored aliasing path judgment threshold. The monitoring data is collected by the edge terminal according to the sampling frequency and the calculation depth. Step S2: Associate the monitoring data with the acquired real abnormal event tags to obtain the association result; Step S3: Update the aliasing path judgment threshold based on the association result, and send the updated aliasing path judgment threshold to the edge terminal so that the edge terminal can use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0068] Understandably, by associating monitoring data with real anomaly event labels independent of the sampling process, the cloud can obtain objective and independent evaluation criteria for the current monitoring strategy, avoiding circular reasoning based solely on its own sampling data to determine effectiveness. Updating the aliasing path judgment threshold based on the association results and distributing it to the edge allows the edge to use more accurate thresholds for aliasing path judgment in the next monitoring cycle. This continuously optimizes the allocation of resources for sampling, computation, and transmission, forming a closed-loop iterative mechanism of edge acquisition – cloud evaluation – threshold correction – edge rescheduling, gradually improving the effective monitoring coverage across the entire domain.

[0069] Further, step S3 includes: Based on the correlation results, determine the effectiveness of the sampling adjustment and the error in judging the aliasing path; Under the preset coverage lower limit constraint, the current aliasing path judgment threshold is updated according to the sampling adjustment validity and the aliasing path judgment error to obtain the updated aliasing path judgment threshold.

[0070] It should be noted that the effectiveness of sampling adjustment refers to the degree of improvement in anomaly detection performance of the current sampling strategy compared to the previous strategy, measured by comparing the difference in the overall sampling utility between the two rounds. Aliasing path judgment error is the deviation of the current aliasing path judgment threshold in distinguishing truly related branches from unrelated branches, including both mistakenly classifying unrelated branches as related and failing to classify related branches as unrelated. The preset coverage lower limit constraint is the minimum percentage of effective monitoring coverage that must be maintained across the entire domain, ensuring that threshold updates do not lead to a decrease in monitoring integrity.

[0071] Understandably, the approach involves first quantifying whether the sampling adjustments truly improve performance through correlation results, thus avoiding blind adjustments; then, a coverage lower limit constraint is introduced to ensure that threshold updates do not sacrifice the basic monitoring capabilities for ordinary branches. Finally, the threshold updates are driven by comprehensively considering the effectiveness of sampling adjustments and the error in aliasing path judgment, ensuring that threshold adjustments have both a clear basis for performance improvement and a safe baseline for global coverage, thereby guaranteeing the robustness and controllability of the closed-loop correction process.

[0072] In practice, after the cloud-based system associates the monitoring data with the actual abnormal event labels, it first calculates the overall sampling utility of this round according to the sampling utility formula. and the previous round If the difference exceeds the preset utility improvement threshold, the comparison will be made. If so, the sampling adjustment is deemed valid. Simultaneously, the cloud calculates the current effective monitoring coverage across the entire area. This ensures that the threshold is not lower than the system's preset lower limit. When both conditions are met simultaneously, the cloud enters the threshold update process; otherwise, it skips this round of updates. During the update process, the cloud calculates the false inclusion rate and false exclusion rate of aliased paths based on the association results and adjusts the threshold according to the four types of operating conditions.

[0073] Specifically, the formula for the overall utility of sampling is: ; in, For the first Overall efficiency of round-trip iterative sampling; , The first Recall rate and precision of abnormal rounds; For the first Average anomaly detection delay per round; For the first Average communication resource overhead per round; , , , The weights are respectively for recall, precision, latency, and cost.

[0074] Furthermore, the error in judging aliasing paths also includes the false inclusion rate and the missed inclusion rate of aliasing paths; Optionally, under a preset coverage lower limit constraint, the step of updating the current aliasing path judgment threshold based on the sampling adjustment validity and the aliasing path judgment error to obtain the updated aliasing path judgment threshold further includes: Under the preset coverage lower limit constraint, if the sampling adjustment validity meets the preset validity condition, then the branch pairs that actually have abnormal associations are determined according to the association results; The aliasing path under-inclusion rate is obtained by calculating the proportion of branch pairs whose overall aliasing relationship is lower than the current aliasing path judgment threshold. If the false inclusion rate of the aliasing path is higher than the preset false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the preset false omission rate threshold, then the current aliasing path judgment threshold is increased to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is lowered to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the false omission rate threshold, then the current aliasing path judgment threshold remains unchanged, and the updated aliasing path judgment threshold is obtained. If the false inclusion rate of the aliasing path is higher than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is updated according to the recalibrated basic parameters to obtain the updated aliasing path judgment threshold.

[0075] It should be noted that the false inclusion rate of aliased paths is the proportion of branch pairs identified as having aliased paths, but which do not actually have a genuine anomaly association. The false inclusion rate of aliased paths is the proportion of branch pairs with a genuine anomaly association, but which were not identified as having aliased paths. The validity condition is that the improvement in the overall utility of the sampling adjustment reaches the preset utility improvement threshold, and the effective monitoring coverage of the entire domain is not lower than the preset lower limit. A branch pair with a genuine anomaly association is two branches confirmed to be simultaneously affected by the same anomaly event based on the real anomaly event label. The false inclusion rate threshold and the false inclusion rate threshold are pre-set critical values ​​used to determine whether false inclusion and false inclusion are serious. The basic parameters for recalibration include, but are not limited to, the analysis window length, the topological neighborhood range, and the correlation weighting coefficient. When both the false inclusion rate and the false inclusion rate are high, it indicates that the current threshold and related parameters are not well-matched, and recalibration is required rather than simply adjusting the threshold.

[0076] Understandably, by separately calculating the false positive rate and the missed positive rate, we can accurately pinpoint the direction and extent to which the current threshold deviates from the ideal value. That is, when the false positive rate is high and the missed positive rate is low, it indicates that the threshold is too low, causing too many irrelevant branches to be included; raising the threshold can reduce false alarms. When the false positive rate is low and the missed positive rate is high, it indicates that the threshold is too high, causing true associations to be missed; lowering the threshold can improve sensitivity. When both are low, it indicates that the threshold is currently suitable and no adjustment is needed. When both are high, it indicates that the root cause is not the threshold itself, but rather an unreasonable setting of the basic analysis parameters, requiring recalibration. This differentiated processing strategy for different scenarios can make threshold updates more scientific and effective.

[0077] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the automatic monitoring method for low-voltage power distribution lines in this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0078] This application also provides an automatic monitoring device for the condition of low-voltage power distribution lines. Please refer to [link / reference]. Figure 5 The low-voltage power distribution line status automatic monitoring device includes: The data acquisition module 10 is used to acquire the original electrical data of each branch in the low-voltage power distribution line; The calculation module 20 is used to perform time-scale weighting and multi-scale correlation calculation on the original electrical data, and then combine it with the pre-stored aliasing path judgment threshold to obtain the aliasing intensity and effective aliasing path number of each branch correlation. The sorting module 30 is used to jointly allocate the sampling frequency, calculation depth and transmission mode of each branch according to the aliasing intensity and the number of effective aliasing paths, and generate the monitoring priority of each branch. The monitoring module 40 is used to collect monitoring data according to the sampling frequency and the calculation depth, and upload the monitoring data to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results. The update module 50 is used to receive the updated aliasing path judgment threshold sent from the cloud and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

[0079] The low-voltage power distribution line status automatic monitoring device provided in this application, employing the low-voltage power distribution line status automatic monitoring method in the above embodiments, can solve the technical problem of low monitoring coverage of low-voltage power distribution line status due to the inability to effectively monitor all branches. Compared with the prior art, the beneficial effects of the low-voltage power distribution line status automatic monitoring device provided in this application are the same as those of the low-voltage power distribution line status automatic monitoring method provided in the above embodiments, and other technical features in the low-voltage power distribution line status automatic monitoring device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0080] This application provides an automatic monitoring device for the status of low-voltage power distribution lines. The automatic monitoring device for the status of low-voltage power distribution lines includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the automatic monitoring method for the status of low-voltage power distribution lines in the first embodiment described above.

[0081] The following is for reference. Figure 6 The diagram illustrates a structural schematic of an automatic monitoring device for the status of low-voltage power distribution lines suitable for implementing embodiments of this application. The automatic monitoring device for the status of low-voltage power distribution lines in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, personal digital assistants, tablets, portable multimedia players, and vehicle terminals (e.g., vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 6 The illustrated low-voltage power distribution line status automatic monitoring device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0082] like Figure 6As shown, the automatic monitoring device for the status of low-voltage power distribution lines may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in ROM (Read Only Memory) 1002 or the program loaded from storage device 1003 into RAM (Random Access Memory) 1004. RAM 1004 also stores various programs and data required for the operation of the automatic monitoring device for the status of low-voltage power distribution lines. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via bus 1005. I / O (input / output) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows the low-voltage distribution line condition automatic monitoring equipment to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows a low-voltage distribution line condition automatic monitoring equipment with various systems, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems can be implemented alternatively.

[0083] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0084] The low-voltage power distribution line status automatic monitoring device provided in this application, employing the low-voltage power distribution line status automatic monitoring method in the above embodiments, can solve the technical problem of low monitoring coverage of low-voltage power distribution line status due to the inability to effectively monitor all branches. Compared with the prior art, the beneficial effects of the low-voltage power distribution line status automatic monitoring device provided in this application are the same as those of the low-voltage power distribution line status automatic monitoring method provided in the above embodiments, and other technical features of this low-voltage power distribution line status automatic monitoring device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0085] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0086] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0087] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the low-voltage power distribution line status automatic monitoring method in the above embodiments.

[0088] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0089] The aforementioned computer-readable storage medium may be included in the automatic monitoring equipment for the condition of low-voltage power distribution lines; or it may exist independently and not be assembled into the automatic monitoring equipment for the condition of low-voltage power distribution lines.

[0090] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by the low-voltage distribution line status automatic monitoring device, cause the low-voltage distribution line status automatic monitoring device to perform the low-voltage distribution line status automatic monitoring method in the above embodiments.

[0091] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation that may be implemented in systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0094] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described automatic monitoring method for the condition of low-voltage power distribution lines. This solves the technical problem of insufficient monitoring coverage of low-voltage power distribution line conditions due to the inability to effectively monitor all branches. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the automatic monitoring method for the condition of low-voltage power distribution lines provided in the above embodiments, and will not be repeated here.

[0095] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the automatic monitoring method for the status of low-voltage power distribution lines as described above.

[0096] The computer program product provided in this application can solve the technical problem that the inability to effectively monitor all branches leads to low coverage of monitoring of the status of low-voltage power distribution lines. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the automatic monitoring method for the status of low-voltage power distribution lines provided in the above embodiments, and will not be repeated here.

[0097] The above description is only a part of the embodiments of this application and does not limit the scope of protection of this application. All equivalent structural transformations made under the technical concept of this application and using the content of this application specification and drawings, or direct / indirect applications in other related technical fields, are included in the scope of protection of this application.

Claims

1. A method for automatic monitoring of the state of a low-voltage distribution line, characterized in that, When applied to the edge, the method includes: Collect raw electrical data for each branch of the low-voltage power distribution line; After performing time-scale weighting and multi-scale correlation calculation on the original electrical data, and combining it with the pre-stored aliasing path judgment threshold, the aliasing intensity and effective aliasing path number of each branch correlation are obtained. Based on the aliasing intensity and the number of effective aliasing paths, the sampling frequency, computation depth and transmission mode of each branch are jointly allocated to generate the monitoring priority of each branch. The monitoring data is collected according to the sampling frequency and the calculation depth, and uploaded to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results. Receive the updated aliasing path judgment threshold from the cloud and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

2. The method of claim 1, wherein the low voltage distribution line condition is automatically monitored by, After performing time-scale weighting and multi-scale correlation calculation on the original electrical data, and combining it with a pre-stored aliasing path judgment threshold, the steps to obtain the aliasing intensity and effective aliasing path number of each branch correlation include: Based on the original electrical data, a time series is generated according to a unified time scale, and the multi-scale correlation between each branch is calculated. Based on the multi-scale correlation, preset constraint information and pre-stored aliasing path judgment threshold, the comprehensive aliasing relationship of each branch is determined. The constraint information includes preset topological constraints, preset abnormal window identifiers and preset data credibility. Based on the comprehensive aliasing relationship and the aliasing path judgment threshold, the aliasing intensity and the number of effective aliasing paths of each branch correlation are obtained.

3. The method of claim 2, wherein the low voltage distribution line condition is automatically monitored by, The steps for obtaining the aliasing intensity and effective aliasing path number of each branch correlation based on the comprehensive aliasing relationship and the aliasing path judgment threshold include: Based on the comprehensive aliasing relationship, within a preset topological neighborhood, each branch is weighted according to a preset weighting coefficient to obtain the weighted aliasing amount of each branch. The weighting coefficient is determined based on a preset topological distance and a preset branch capacity. When the weighted aliasing amount satisfies the preset aliasing interval rules, the aliasing interval of each branch is determined. The aliasing interval rules include a start threshold, an exit threshold, and a minimum maintenance duration. Within the aliasing interval, the number of branches that meet the aliasing condition in each branch is counted. The aliasing condition is that the comprehensive aliasing relationship in the topological neighborhood is greater than or equal to the aliasing path judgment threshold. The weighted aliasing amount is used as the aliasing intensity of each branch correlation, and the number of branches is used as the number of effective aliasing paths.

4. The method of claim 2, wherein the low voltage distribution line condition is automatically monitored by, Based on the original electrical data, the steps for generating time series according to a unified time scale and calculating the multi-scale correlation between branches include: The original electrical data is divided into time intervals according to a unified time scale, and the original electrical data falling into the same time interval are weighted and aggregated according to the sampling interval of each sampling time to obtain the time series values ​​of each branch at the three time scales of seconds, minutes and hours. Calculate the temporal variation of each branch based on the temporal values ​​of adjacent time intervals; Based on the time series value, the preset importance coefficient of the electrical state quantity and the preset data reliability weight, calculate the same-scale amplitude correlation coefficient between each branch, and based on the time series change, the importance coefficient and the data reliability weight, calculate the same-scale trend correlation coefficient between each branch. Based on the temporal changes of each branch at different time scales, cross-correlation calculations are performed on the temporal changes to obtain cross-correlation values ​​that vary with relative time delay, and the maximum value among the cross-correlation values ​​is taken as the cross-scale correlation strength. The multi-scale correlation between branches is obtained based on the same-scale amplitude correlation coefficient, the same-scale trend correlation coefficient, and the cross-scale correlation strength.

5. A method for automatic monitoring of the state of a low voltage distribution line, characterized in that When applied in the cloud, the method includes: The edge terminal receives monitoring data uploaded according to monitoring priority and transmission mode. The monitoring priority is generated by the edge terminal based on the aliasing intensity and the number of effective aliasing paths, and the sampling frequency, calculation depth and transmission mode of each branch are jointly allocated. The aliasing intensity and the number of effective aliasing paths are obtained by the edge terminal by performing time-scale weighting and multi-scale correlation calculation on the original electrical data of each branch in the low-voltage distribution line, and combining it with the pre-stored aliasing path judgment threshold. The monitoring data is collected by the edge terminal according to the sampling frequency and the calculation depth. The monitoring data is correlated with the acquired real abnormal event tags to obtain the correlation results; The aliasing path judgment threshold is updated based on the association result, and the updated aliasing path judgment threshold is sent to the edge terminal so that the edge terminal can use the updated aliasing path judgment threshold for subsequent branch status monitoring.

6. The method of claim 5, wherein the low voltage distribution line condition is automatically monitored by, The step of updating the aliasing path determination threshold based on the association result includes: Based on the correlation results, determine the effectiveness of the sampling adjustment and the error in judging the aliasing path; Under the preset coverage lower limit constraint, the current aliasing path judgment threshold is updated according to the sampling adjustment validity and the aliasing path judgment error to obtain the updated aliasing path judgment threshold.

7. The method of claim 6, wherein the step of automatically monitoring the status of the low voltage distribution line comprises the step of: The aliasing path judgment error includes the aliasing path false inclusion rate and the aliasing path missed inclusion rate; ​ Under a preset coverage lower limit constraint, the step of updating the current aliasing path judgment threshold based on the sampling adjustment effectiveness and the aliasing path judgment error to obtain the updated aliasing path judgment threshold includes: Under the preset coverage lower limit constraint, if the sampling adjustment validity meets the preset validity condition, then the branch pairs that actually have abnormal associations are determined according to the association results; The aliasing path under-inclusion rate is obtained by calculating the proportion of branch pairs whose overall aliasing relationship is lower than the current aliasing path judgment threshold. If the false inclusion rate of the aliasing path is higher than the preset false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the preset false omission rate threshold, then the current aliasing path judgment threshold is increased to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is lowered to obtain the updated aliasing path judgment threshold. If the false inclusion rate of the aliasing path is lower than the false inclusion rate threshold, and the false omission rate of the aliasing path is lower than the false omission rate threshold, then the current aliasing path judgment threshold remains unchanged, and the updated aliasing path judgment threshold is obtained. If the false inclusion rate of the aliasing path is higher than the false inclusion rate threshold, and the false omission rate of the aliasing path is higher than the false omission rate threshold, then the current aliasing path judgment threshold is updated according to the recalibrated basic parameters to obtain the updated aliasing path judgment threshold.

8. A low voltage distribution line condition automatic monitoring apparatus, characterized by, Applied to the edge, the device includes: The data acquisition module is used to collect raw electrical data from each branch of the low-voltage power distribution line. The calculation module is used to perform time-scale weighting and multi-scale correlation calculation on the original electrical data, and then combine it with the pre-stored aliasing path judgment threshold to obtain the aliasing intensity and effective aliasing path number of each branch correlation. The sorting module is used to jointly allocate the sampling frequency, computation depth and transmission mode of each branch according to the aliasing intensity and the number of effective aliasing paths, and generate the monitoring priority of each branch. The monitoring module is used to collect monitoring data according to the sampling frequency and the calculation depth, and upload the monitoring data to the cloud according to the monitoring priority and transmission mode, so that the cloud can associate the monitoring data with real abnormal event tags and update the aliasing path judgment threshold according to the association results; The update module is used to receive the updated aliasing path judgment threshold from the cloud and use the updated aliasing path judgment threshold for subsequent branch status monitoring.

9. A low voltage distribution line condition monitoring apparatus, characterized by, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the automatic monitoring method for the condition of low-voltage power distribution lines as described in any one of claims 1 to 7.

10. A storage medium, characterized by The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the automatic monitoring method for the status of low-voltage power distribution lines as described in any one of claims 1 to 7.