Intelligent operation and maintenance management platform for power distribution network

Abstract

The invention relates to the technical field of power distribution network monitoring, in particular to an intelligent operation and maintenance management platform for a power distribution network. Obtaining suspected abnormal points according to data discrete features and local data fluctuation features of the feature data sequence; according to the number characteristics of the suspected abnormal points in all the operation and maintenance characteristics and the data distribution characteristics of the suspected abnormal points, risk statistical characteristic values of the power distribution network equipment are obtained; clustering suspected abnormal points in the operation and maintenance features, and obtaining risk distribution feature values of the power distribution network equipment according to time interval features between the data point clusters and interval features of the suspected abnormal points in the data point clusters; and obtaining the risk degree of the power distribution network equipment according to the risk statistical characteristic value and the risk distribution characteristic value. According to the invention, the inspection sequence of all power distribution network equipment is sorted according to the risk degree, and inspection is carried out in sequence, so that the inspection efficiency and the power utilization stability are improved.

Description

Technical Field

[0001] This invention relates to the field of power distribution network monitoring technology, and more specifically to an intelligent operation and maintenance management platform for power distribution networks. Background Technology

[0002] The power distribution network is a crucial link connecting power sources and end users. Proper operation and maintenance management of distribution network equipment enables timely detection and handling of potential problems, reduces equipment failure rates, and ensures stable power supply for production and daily life. Currently, the maintenance and inspection sequence for distribution network equipment is typically repeated in chronological order based on historical inspections. However, due to the varying operating conditions of different distribution network devices, some are more prone to anomalies. Given the large number and wide distribution of distribution network equipment, completing a single inspection cycle is time-consuming. Following a chronological inspection approach can lead to untimely maintenance of vulnerable equipment, potentially causing grid faults and reduced power stability. Therefore, the chronological approach to distribution network equipment operation and maintenance management is inefficient and prone to power outages. Summary of the Invention

[0003] To address the aforementioned technical problems, the present invention aims to provide an intelligent operation and maintenance management platform for power distribution networks. The specific technical solution adopted is as follows: The data acquisition module is used to acquire feature data sequences of different operation and maintenance characteristics of the monitoring power distribution network equipment; The first data analysis module is used to obtain the degree of anomaly of data points based on the data discreteness and local data fluctuation characteristics of the feature data sequence; to obtain suspected anomalies based on the degree of anomaly; and to obtain the risk statistical characteristic value of the power distribution network equipment based on the number of suspected anomalies and the data distribution characteristics of the suspected anomalies in all operation and maintenance characteristics. The second data analysis module is used to cluster suspected anomalies in the operation and maintenance characteristics to obtain different data point clusters; and to obtain the risk distribution characteristic value of the power distribution network equipment based on the time interval characteristics between the data point clusters and the interval characteristics of suspected anomalies within the data point clusters. The operation and maintenance module is used to obtain the risk level of the distribution network equipment based on the risk statistical feature value and the risk distribution feature value; sort the inspection order of all distribution network equipment according to the risk level; and inspect the distribution network equipment in sequence according to the sorting result.

[0004] Furthermore, the step of obtaining the degree of anomaly of data points based on the data discreteness characteristics and local data fluctuation characteristics of the feature data sequence includes: Calculate and normalize the absolute value of the difference between the average value of the feature data sequence and any data point to obtain the deviation of the arbitrary data point; calculate and normalize the absolute value of the difference between the arbitrary data point and the previous data point to obtain the volatility of the arbitrary data point; calculate the sum of the deviation and the volatility to obtain the anomaly degree of the arbitrary data point.

[0005] Furthermore, the step of obtaining suspected anomalies based on the degree of anomaly includes: Data points whose anomaly level exceeds a preset anomaly threshold are designated as suspected anomaly points.

[0006] Furthermore, the step of obtaining the risk statistical characteristic value of the distribution network equipment based on the quantity characteristics and data distribution characteristics of suspected anomalies among all operation and maintenance characteristics includes: Calculate and normalize the total number of suspected anomalies for all operation and maintenance features of the distribution network equipment to obtain anomaly density value; calculate and normalize the sum of the deviations of the suspected anomalies for all operation and maintenance features to obtain comprehensive deviation; calculate the sum of the anomaly density value and the comprehensive deviation to obtain the risk statistical feature value of the distribution network equipment.

[0007] Furthermore, the step of clustering suspected anomalies in the operational features to obtain different data point clusters includes: The suspected anomalies in the operation and maintenance features are clustered using the K-means clustering algorithm to obtain different data point clusters.

[0008] Further, the step of obtaining the risk distribution characteristic value of the power distribution network equipment based on the time interval characteristics between the data point clusters and the interval characteristics of suspected anomalies within the data point clusters includes: Calculate the standard deviation of the time interval between adjacent suspected anomalies within the data point cluster to obtain the interval disorder; calculate the average of all interval disorder values ​​for the data point cluster corresponding to the operation and maintenance feature to obtain the average interval disorder; calculate the sum of the average interval disorder values ​​of all operation and maintenance features and normalize it to obtain the first distribution complexity; calculate the standard deviation of the time interval between the data point clusters of the operation and maintenance feature to obtain the first value; calculate the sum of the first values ​​of all operation and maintenance features and normalize it to obtain the second distribution complexity; calculate the sum of the first distribution complexity and the second distribution complexity to obtain the risk distribution characteristic value of the distribution network equipment.

[0009] Further, the step of obtaining the risk level of the distribution network equipment based on the risk statistical characteristic value and the risk distribution characteristic value includes: The risk level of the power distribution network equipment is obtained by calculating the sum of the risk statistical characteristic value and the risk distribution characteristic value.

[0010] Furthermore, the step of sorting the inspection sequence of all distribution network equipment according to the risk level includes: All distribution network equipment is sorted in descending order of risk level to obtain the inspection sequence of the distribution network equipment.

[0011] The present invention has the following beneficial effects: In this invention, the degree of anomaly of acquired data points can reflect the abnormal characteristics of different data points in a feature data sequence, thereby filtering out suspected anomalies. Suspected anomalies can characterize the most abnormal moments in the feature data sequence. Since the operating status of distribution network equipment affects the stability of user power supply, distribution network equipment with a high risk of faults should be prioritized for maintenance. Acquiring risk statistical feature values ​​can reflect the abnormal operating conditions of distribution network equipment based on the quantity and distribution characteristics of suspected anomalies. Acquiring data point clusters can cluster suspected anomalies from different times, facilitating the analysis of their distribution patterns. Acquiring risk distribution feature values ​​can reflect the abnormal operating conditions of distribution network equipment based on the time interval characteristics between data point clusters and the interval characteristics of suspected anomalies within a data point cluster. The degree of risk can characterize the stability of the operating status of distribution network equipment and its impact on power grid operation. Finally, the inspection order of all distribution network equipment is ranked according to the degree of risk, and the equipment is inspected sequentially based on the ranking result, improving the inspection efficiency and power supply stability of the distribution network. Attached Figure Description

[0012] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a block diagram of an intelligent operation and maintenance management platform for power distribution networks provided in one embodiment of the present invention. Detailed Implementation

[0014] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent operation and maintenance management platform for power distribution networks proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0016] The following description, in conjunction with the accompanying drawings, details the specific solution of the intelligent operation and maintenance management platform for power distribution networks provided by this invention.

[0017] Please see Figure 1 The diagram illustrates a block diagram of an intelligent operation and maintenance management platform for a power distribution network according to an embodiment of the present invention. The platform includes the following modules: The data acquisition module S1 is used to acquire feature data sequences of different operation and maintenance characteristics of the monitoring power distribution network equipment.

[0018] In this embodiment of the invention, the implementation scenario is to perform operation and maintenance management on distribution network equipment to improve inspection efficiency and power supply stability. First, characteristic data sequences of different operation and maintenance features of the distribution network equipment are acquired. Common operation and maintenance features in distribution cabinets include operating voltage, operating current, equipment temperature, and equipment humidity. These features can be used to preliminarily determine the operating status of the distribution cabinet. Starting from the end of the last inspection, data for each operation and maintenance feature is collected every minute, thus obtaining four characteristic data sequences for the distribution cabinet. The implementer can determine the distribution network equipment objects and the operation and maintenance features to be monitored based on the implementation scenario. After obtaining the characteristic data sequences of all distribution cabinets, the order of inspections of the distribution cabinets can be analyzed based on the characteristic data sequences, thereby improving power supply stability.

[0019] The first data analysis module S2 is used to obtain the degree of anomaly of data points based on the data discreteness and local data fluctuation characteristics of the feature data sequence; to obtain suspected anomalies based on the degree of anomaly; and to obtain the risk statistical characteristic value of the distribution network equipment based on the number of suspected anomalies and the data distribution characteristics of suspected anomalies in all operation and maintenance characteristics.

[0020] The higher the probability of a suspected abnormal situation occurring during the operation of a distribution cabinet, the more priority should be given to maintaining this distribution cabinet in the next round of inspections to reduce the potential for power grid faults and improve power stability. Therefore, the abnormal operating state of the distribution cabinet can be analyzed based on characteristic data sequences. During the operation of the distribution cabinet, compared with normal data values, the deviation of suspected abnormal data points in the characteristic data sequence is greater, the data is more discrete, and there may be significant fluctuations in data at adjacent times. Therefore, the degree of abnormality of data points is obtained based on the data discreteness characteristics and local data fluctuation characteristics of the characteristic data sequence. Preferably, in this embodiment of the invention, the step of obtaining the degree of abnormality includes: calculating the absolute value of the difference between the average value of the characteristic data sequence and any data point and normalizing it to obtain the deviation of the arbitrary data point. The average value of the data represents the average level of the characteristic data sequence. The greater the deviation, the more the value of the data point deviates from the average level, and the more unstable the operating state of the distribution cabinet may be at that moment, and the more likely an abnormal situation may occur. In this embodiment of the invention, the normalization method is the existing maximum and minimum value normalization method. Calculate the absolute value of the difference between any data point and the previous data point and normalize it to obtain the volatility of that data point. A higher volatility indicates a greater difference between adjacent data points, more pronounced abrupt changes, and potentially more unstable operation of the distribution cabinet at that moment. Calculate the sum of the deviation and volatility to obtain the degree of anomaly for that data point. A higher degree of anomaly indicates a greater likelihood of potential faults in the distribution cabinet at that moment, and a greater likelihood of affecting power supply stability.

[0021] Furthermore, after obtaining the degree of anomaly of different data points in the feature data sequence, suspected anomalies in the feature data sequence can be identified. Therefore, suspected anomalies are obtained based on the degree of anomaly, specifically including: data points whose degree of anomaly exceeds a preset anomaly threshold as suspected anomalies; after normalization, the value range of the degree of anomaly is 0 to 2. When the value of a data point is more stable and tends to the average level, its degree of anomaly is closer to 0; conversely, the more abnormal the data point, the closer its degree of anomaly is to 2. The two are distributed at both ends of the value range. Therefore, in this embodiment of the invention, the preset anomaly threshold is 1. A suspected anomaly means that the working state of the power distribution cabinet at that moment is more likely to be abnormal, which is likely to affect the stability of power supply.

[0022] After identifying suspected anomalies in all maintenance features of the distribution cabinet, it is necessary to analyze the overall operating status of the distribution cabinet to determine its degree of risk. The more suspected anomalies there are in each maintenance feature of the distribution cabinet, and the greater the degree of anomaly, the worse the operating status of the distribution cabinet, the higher the probability of subsequent failures, and the more likely it is to cause potential electrical hazards. Furthermore, based on the quantity and distribution characteristics of suspected anomalies in all maintenance features, the risk statistical characteristic value of the distribution network equipment is obtained. Preferably, in this embodiment of the invention, the step of obtaining the risk statistical characteristic value includes: calculating and normalizing the total number of suspected anomalies in all maintenance features of the distribution network equipment to obtain an anomaly density value; the larger the anomaly density value, the more suspected anomalies the distribution cabinet has experienced in its historical operation, the more unstable its operating status, and the greater the possibility of potential electrical hazards. The sum of the deviations of the suspected anomalies in all maintenance features is calculated and normalized to obtain the comprehensive deviation; the larger the comprehensive deviation, the more obvious the data anomaly characteristics, and the weaker the operating stability of the distribution cabinet. The sum of the abnormal density value and the comprehensive deviation is calculated to obtain the risk statistical characteristic value of the distribution network equipment. The larger the risk statistical characteristic value of the distribution network equipment, the lower the reliability of the distribution cabinet's operating status, and the more timely the maintenance is required.

[0023] The second data analysis module S3 is used to cluster suspected anomalies in the operation and maintenance characteristics to obtain different data point clusters; and to obtain the risk distribution characteristic value of the distribution network equipment based on the time interval characteristics between data point clusters and the interval characteristics of suspected anomalies within the data point clusters.

[0024] Since data fluctuations in distribution network equipment cannot fully represent abnormal equipment behavior, some power dispatching or load change events can also cause significant fluctuations in operation and maintenance (O&M) characteristic data. However, compared to the fluctuations in true abnormal data, these dispatching or load change-induced data fluctuations usually exhibit regularity, while the fluctuations in true abnormal data are more complex. Therefore, suspected anomalies in O&M characteristics are clustered to obtain different data point clusters. Specifically, this involves using the K-means clustering algorithm to cluster suspected anomalies in O&M characteristics to obtain different data point clusters. It should be noted that the K-means clustering algorithm is an existing technology, and the specific steps will not be elaborated further. The time intervals between suspected anomalies within data point clusters are relatively short, while the time intervals between suspected anomalies between different data point clusters are relatively long. Furthermore, the distribution pattern characteristics of suspected anomalies can be analyzed based on the data point clusters. Therefore, the risk distribution characteristic values ​​of distribution network equipment can be obtained based on the time interval characteristics between data point clusters and the interval characteristics of suspected anomalies within data point clusters.

[0025] Preferably, in this embodiment of the invention, the step of obtaining the risk distribution characteristic value includes: calculating the standard deviation of the time interval between adjacent suspected anomalies within a data point cluster to obtain the interval disorder; the more similar the time intervals, the smaller the interval disorder, meaning that the data fluctuations are more likely to be caused by regular events influenced by human factors such as power dispatch or load changes; the larger the interval disorder, the more random the distribution of suspected anomalies, and the more likely it is caused by the unstable operation of the distribution cabinet. Calculate the average interval disorder of all intervals for the corresponding data point cluster of the operation and maintenance feature to obtain the average interval disorder; the larger the average interval disorder, the worse the working condition of the distribution cabinet. Calculate the sum of the average interval disorder of all operation and maintenance features and normalize it to obtain the first distribution complexity; the larger the first distribution complexity, the more unstable the operating condition of the distribution cabinet, and the more likely it is to affect the stability of power consumption. Calculate the standard deviation of the time interval between the data point clusters of the operation and maintenance feature to obtain a first value; the time interval between data point clusters is the time interval between the closest suspected anomalies in two clusters; the smaller the first value, the more similar the time intervals of the fluctuation characteristics represented by different data point clusters, and the more regular the data changes of the characteristic data sequence of the operation and maintenance feature. Calculate the sum of the first values ​​of all operation and maintenance characteristics and normalize them to obtain the second distribution complexity. A larger second distribution complexity indicates a more unstable operating state and a higher probability of failure for the distribution cabinet. Calculate the sum of the first and second distribution complexities to obtain the risk distribution characteristic value of the distribution network equipment. A larger risk distribution characteristic value indicates a more unstable operating state for the distribution cabinet, a higher likelihood of grid failures, and an impact on power supply stability. The formulas for obtaining the risk distribution characteristic value include:

[0026] In the formula, R represents the risk distribution characteristic value of the distribution cabinet. This represents normalization, and N represents the number of operational features. This represents the number of data point clusters representing the nth operational feature. This represents the interval disorder of the m-th data point cluster in the operational feature n. Indicates the average interval disorder. Indicates the first distribution complexity. Indicates the first value. This represents the second distribution complexity.

[0027] The operation and maintenance module S4 is used to obtain the risk level of distribution network equipment based on risk statistical characteristic values ​​and risk distribution characteristic values; sort the inspection order of all distribution network equipment according to the risk level; and inspect the distribution network equipment in sequence according to the sorting result.

[0028] After obtaining the risk statistical characteristic value and risk distribution characteristic value, the risk level of the distribution network equipment can be obtained based on these values. Preferably, in this embodiment of the invention, the step of obtaining the risk level includes: calculating the sum of the risk statistical characteristic value and the risk distribution characteristic value to obtain the risk level of the distribution network equipment. A higher risk level means a more unstable operating state of the distribution network, a higher probability of subsequent faults, and a greater likelihood of grid failures, affecting power stability. Therefore, maintenance should be prioritized during inspections. After obtaining the risk levels of all distribution cabinets, the inspection order of all distribution network equipment can be sorted according to the risk level. The equipment is then inspected sequentially based on the sorting result. Specifically, this includes sorting all distribution network equipment in descending order of risk level to obtain the inspection order. A higher risk level requires priority maintenance and inspection of the equipment to reduce the probability of potential faults and avoid situations where prolonged inspections result in some less stable distribution network equipment not being maintained in time, thus preventing grid failures. Therefore, prioritizing the inspection sequence of distribution cabinets according to their risk level can significantly improve equipment inspection efficiency, allowing for the maintenance of distribution network equipment with a higher probability of failure, thereby improving power stability and reducing the risk of power anomalies.

[0029] In summary, this invention provides an intelligent operation and maintenance management platform for power distribution networks. It identifies suspected anomalies based on the data discreteness and local data fluctuation characteristics of feature data sequences. It obtains risk statistical characteristic values ​​for power distribution network equipment based on the quantity and distribution characteristics of suspected anomalies across all operation and maintenance features. The platform then clusters suspected anomalies within the operation and maintenance features, obtaining risk distribution characteristic values ​​for the power distribution network equipment based on the time interval between data point clusters and the interval between suspected anomalies within each cluster. Finally, it determines the risk level of the power distribution network equipment based on the risk statistical characteristic values ​​and the risk distribution characteristic values. This invention sorts the inspection sequence of all power distribution network equipment according to the risk level and performs inspections sequentially, improving inspection efficiency and power supply stability.

[0030] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0031] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A smart operation and maintenance management platform for power distribution networks, characterized in that, The platform includes the following modules: The data acquisition module is used to acquire feature data sequences of different operation and maintenance characteristics of the monitoring power distribution network equipment; The first data analysis module is used to obtain the degree of anomaly of data points based on the data discreteness and local data fluctuation characteristics of the feature data sequence; to obtain suspected anomalies based on the degree of anomaly; and to obtain the risk statistical characteristic value of the power distribution network equipment based on the number of suspected anomalies and the data distribution characteristics of the suspected anomalies in all operation and maintenance characteristics. The second data analysis module is used to cluster suspected anomalies in the operation and maintenance characteristics to obtain different data point clusters; and to obtain the risk distribution characteristic value of the power distribution network equipment based on the time interval characteristics between the data point clusters and the interval characteristics of suspected anomalies within the data point clusters. The operation and maintenance module is used to obtain the risk level of the power distribution network equipment based on the risk statistical characteristic value and the risk distribution characteristic value; The inspection sequence of all power distribution network equipment is sorted according to the risk level, and the equipment is inspected sequentially according to the sorting result.

2. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of obtaining the degree of anomaly of data points based on the data discrete characteristics and local data fluctuation characteristics of the feature data sequence includes: Calculate and normalize the absolute value of the difference between the average value of the feature data sequence and any data point to obtain the deviation of the arbitrary data point; calculate and normalize the absolute value of the difference between the arbitrary data point and the previous data point to obtain the volatility of the arbitrary data point; calculate the sum of the deviation and the volatility to obtain the anomaly degree of the arbitrary data point.

3. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of obtaining suspected anomalies based on the degree of anomaly includes: Data points whose anomaly level exceeds a preset anomaly threshold are designated as suspected anomaly points.

4. The intelligent operation and maintenance management platform for power distribution networks according to claim 2, characterized in that, The step of obtaining the risk statistical characteristic value of the power distribution network equipment based on the quantity characteristics and data distribution characteristics of suspected anomalies among all operation and maintenance characteristics includes: Calculate and normalize the total number of suspected anomalies for all operation and maintenance features of the distribution network equipment to obtain anomaly density value; calculate and normalize the sum of the deviations of the suspected anomalies for all operation and maintenance features to obtain comprehensive deviation; calculate the sum of the anomaly density value and the comprehensive deviation to obtain the risk statistical feature value of the distribution network equipment.

5. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of clustering suspected anomalies in the operational features to obtain different data point clusters includes: The suspected anomalies in the operation and maintenance features are clustered using the K-means clustering algorithm to obtain different data point clusters.

6. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of obtaining the risk distribution characteristic value of the power distribution network equipment based on the time interval characteristics between data point clusters and the interval characteristics of suspected anomalies within data point clusters includes: Calculate the standard deviation of the time interval between adjacent suspected anomalies within the data point cluster to obtain the interval disorder; calculate the average of all interval disorder values ​​for the data point cluster corresponding to the operation and maintenance feature to obtain the average interval disorder; calculate the sum of the average interval disorder values ​​of all operation and maintenance features and normalize it to obtain the first distribution complexity; calculate the standard deviation of the time interval between the data point clusters of the operation and maintenance feature to obtain the first value; calculate the sum of the first values ​​of all operation and maintenance features and normalize it to obtain the second distribution complexity; calculate the sum of the first distribution complexity and the second distribution complexity to obtain the risk distribution characteristic value of the distribution network equipment.

7. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of obtaining the risk level of the power distribution network equipment based on the risk statistical characteristic value and the risk distribution characteristic value includes: The risk level of the power distribution network equipment is obtained by calculating the sum of the risk statistical characteristic value and the risk distribution characteristic value.

8. The intelligent operation and maintenance management platform for power distribution networks according to claim 1, characterized in that, The step of sorting the inspection sequence of all power distribution network equipment according to the risk level includes: All distribution network equipment is sorted in descending order of risk level to obtain the inspection sequence of the distribution network equipment.

Images