Average power failure duration monitoring method and device based on index blood relationship map, computer equipment, storage medium and computer program product

Abstract

The invention relates to an average power failure duration monitoring method and device based on an index blood relationship map, computer equipment, a storage medium and a computer program product. The method comprises the following steps: continuously acquiring voltage signals from a low-voltage telemetering system, judging whether a continuous low-voltage section exists or not according to the voltage signals through a preset threshold value, and screening candidate power failure sections meeting the minimum duration in combination with a sliding window algorithm; carrying out matching verification on the candidate power failure sections and a fault recovery record of the work order system, and generating a standardized power failure event table containing starting and ending time and a region to which the candidate power failure sections belong; calculating an average power failure duration index based on the standardized power failure event table aggregation according to a specified area and a time window; constructing a directed consanguinity map according to the average power failure duration index; the method comprises the following steps: establishing a dynamic baseline according to historical data, performing anomaly detection on a real-time index, backtracking upwards through a directed consanguinity map to position an abnormal root cause under the condition that the index is detected to be abnormal, and generating a diagnosis suggestion. The method can improve the abnormality diagnosis efficiency.

Description

Technical Field

[0001] This application relates to the field of signal acquisition technology, and in particular to a method, device, computer equipment, storage medium and computer program product for monitoring average power outage duration based on index lineage maps. Background Technology

[0002] With the continuous advancement of intelligent power distribution network construction, power supply service continuity and fault response efficiency have become core standards for measuring the quality of power operation. Among them, average outage duration, as a key assessment indicator, is widely used in core scenarios such as dispatch optimization, service quality assessment, and emergency response decision-making, and is directly related to the accuracy of power system operation and maintenance management and users' electricity experience.

[0003] However, existing methods for monitoring average power outage duration have significant technical bottlenecks and are difficult to adapt to the actual needs of intelligent operation of distribution networks. Traditional solutions generally rely on manual statistics of discrete work orders and static report generation, lacking the ability to structure and model the entire process of indicator generation, and failing to achieve full-chain traceability from raw data collection and intermediate processing logic to final indicator output.

[0004] Therefore, there is an urgent need for an average power outage duration monitoring technology that can integrate multi-source heterogeneous data, realize the visualization and traceability of indicator generation paths, and improve the efficiency of anomaly diagnosis, so as to break through the existing technical bottlenecks and provide reliable technical support for the high-quality operation of the distribution network. Summary of the Invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for monitoring average power outage duration based on indicator lineage maps, which can integrate multi-source heterogeneous data, realize visualized traceability of indicator generation paths, and improve the efficiency of anomaly diagnosis, in order to address the above-mentioned technical problems.

[0006] Firstly, this application provides a method for monitoring average power outage duration based on an indicator lineage map. The method includes:

[0007] Voltage signals are continuously collected from the low-voltage telemetry system. A preset threshold is used to determine whether there are continuous low-voltage sections based on the voltage signals. A sliding window algorithm is then used to filter candidate power outage sections that meet the minimum duration.

[0008] The candidate power outage segments are matched and verified with the fault recovery records of the work order system to generate a standardized power outage event table that includes start and end times and the area to which the outage belongs.

[0009] The average power outage duration index is calculated by aggregating and calculating based on the standardized power outage event table according to the specified region and time window.

[0010] A directed lineage map is constructed based on the average power outage duration index;

[0011] A dynamic baseline is established based on historical data, and anomalies are detected in real-time indicators. When anomalies are detected, the root cause of the anomaly is located by tracing back upwards through the directed lineage map, and diagnostic suggestions are generated.

[0012] In some embodiments of the method, the step of continuously acquiring voltage signals from a low-voltage telemetry system, determining whether a continuous low-voltage section exists based on the voltage signals using a preset threshold, and filtering candidate power outage sections that meet the minimum duration using a sliding window algorithm includes:

[0013] Construct a judgment function to identify continuous voltage segments where the voltage signal is below a preset threshold;

[0014] The judgment function outputs either 0 or 1; an output of 0 indicates normal operation, while an output of 1 indicates a possible low-voltage power outage.

[0015] In some embodiments of the method, the step of matching and verifying the candidate power outage segments with the fault recovery records of the work order system to generate a standardized power outage event table containing start and end times and the region to which they belong includes:

[0016] The candidate power outage segment is associated with the fault recovery record by regional identifier, and the degree of overlap in the time range of the candidate power outage segment and the fault recovery record is compared.

[0017] If the degree of overlap meets the preset matching conditions, the match is considered successful.

[0018] In some embodiments of the method, the step of aggregating and calculating the average power outage duration index based on the standardized power outage event table according to a specified region and time window includes:

[0019] Based on the standardized power outage event table, the area and time range to be calculated are determined.

[0020] Calculate the duration of each power outage event in the standardized power outage event table;

[0021] The durations of all power outage events within the specified area and time range are aggregated to obtain the average power outage duration index for the corresponding area and time window.

[0022] In some embodiments of the method, constructing a directed lineage map based on the average power outage duration index includes:

[0023] Obtain all elements related to the average power outage duration indicator, including raw voltage data, power outage event identification logic, power outage event matching and verification logic, indicator aggregation calculation logic, and at least one of the average power outage duration indicators;

[0024] Treat each element as an independent node;

[0025] Based on the dependencies between the relevant elements, directed edges are used to connect the corresponding nodes to form a directed lineage graph;

[0026] The dependencies include the support relationship between the original voltage data and the power outage event identification logic, the input relationship between the power outage event identification results and the matching and verification logic, the supply relationship between the matching and verification power outage event data and the aggregation calculation logic, and the derivation relationship between the aggregation calculation logic and the average power outage duration index.

[0027] In some embodiments of the method, the step of establishing a dynamic baseline based on historical data, detecting anomalies in real-time indicators, and, upon detecting anomalies, tracing back to locate the root cause of the anomaly using the directed lineage map and generating diagnostic suggestions includes:

[0028] Obtain historical operational data on the average power outage duration index, and establish a dynamic baseline based on the historical operational data;

[0029] The average power outage duration index is obtained through real-time calculation. The real-time index is compared with the dynamic baseline to determine whether there are any abnormalities in the real-time index.

[0030] If an anomaly in a real-time indicator is detected, the root cause of the anomaly is investigated by tracing back along the dependency path of the indicator generation based on the directed lineage graph.

[0031] Based on the identified root causes, targeted diagnostic recommendations are generated.

[0032] According to a second aspect of the present disclosure, a device for monitoring average power outage duration based on an index lineage map is provided. The device includes:

[0033] The first module is used to continuously acquire voltage signals from the low-voltage telemetry system, determine whether there are continuous low-voltage sections based on the voltage signals according to a preset threshold, and filter candidate power outage sections that meet the minimum duration by combining a sliding window algorithm.

[0034] The second module is used to match and verify the candidate power outage segments with the fault recovery records of the work order system, and generate a standardized power outage event table that includes start and end times and the area to which the outage belongs.

[0035] The third module is used to aggregate and calculate the average power outage duration index based on the standardized power outage event table according to the specified area and time window.

[0036] The fourth module is used to construct a directed lineage map based on the average power outage duration index;

[0037] The fifth module is used to establish a dynamic baseline based on historical data, detect anomalies in real-time indicators, and, when an anomaly is detected, trace back to locate the root cause of the anomaly through the directed lineage map and generate diagnostic suggestions.

[0038] According to a third aspect of the present disclosure, a computer device is provided. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0039] Voltage signals are continuously collected from the low-voltage telemetry system. A preset threshold is used to determine whether there are continuous low-voltage sections based on the voltage signals. A sliding window algorithm is then used to filter candidate power outage sections that meet the minimum duration.

[0040] The candidate power outage segments are matched and verified with the fault recovery records of the work order system to generate a standardized power outage event table that includes start and end times and the area to which the outage belongs.

[0041] The average power outage duration index is calculated by aggregating and calculating based on the standardized power outage event table according to the specified region and time window.

[0042] A directed lineage map is constructed based on the average power outage duration index;

[0043] A dynamic baseline is established based on historical data, and anomalies are detected in real-time indicators. When anomalies are detected, the root cause of the anomaly is located by tracing back upwards through the directed lineage map, and diagnostic suggestions are generated.

[0044] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0045] Voltage signals are continuously collected from the low-voltage telemetry system. A preset threshold is used to determine whether there are continuous low-voltage sections based on the voltage signals. A sliding window algorithm is then used to filter candidate power outage sections that meet the minimum duration.

[0046] The candidate power outage segments are matched and verified with the fault recovery records of the work order system to generate a standardized power outage event table that includes start and end times and the area to which the outage belongs.

[0047] The average power outage duration index is calculated by aggregating and calculating based on the standardized power outage event table according to the specified region and time window.

[0048] A directed lineage map is constructed based on the average power outage duration index;

[0049] A dynamic baseline is established based on historical data, and anomalies are detected in real-time indicators. When anomalies are detected, the root cause of the anomaly is located by tracing back upwards through the directed lineage map, and diagnostic suggestions are generated.

[0050] According to a fifth aspect of the present disclosure, a computer program product is provided. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0051] Voltage signals are continuously collected from the low-voltage telemetry system. A preset threshold is used to determine whether there are continuous low-voltage sections based on the voltage signals. A sliding window algorithm is then used to filter candidate power outage sections that meet the minimum duration.

[0052] The candidate power outage segments are matched and verified with the fault recovery records of the work order system to generate a standardized power outage event table that includes start and end times and the area to which the outage belongs.

[0053] The average power outage duration index is calculated by aggregating and calculating based on the standardized power outage event table according to the specified region and time window.

[0054] A directed lineage map is constructed based on the average power outage duration index;

[0055] A dynamic baseline is established based on historical data, and anomalies are detected in real-time indicators. When anomalies are detected, the root cause of the anomaly is located by tracing back upwards through the directed lineage map, and diagnostic suggestions are generated.

[0056] The average power outage duration monitoring scheme based on the indicator lineage graph provided in this application realizes the closed-loop management of the average power outage duration indicator from data collection, event identification to anomaly tracing. Through multi-source data fusion and directed lineage graph construction, it solves the problems of scattered data sources, opaque calculation logic, and difficulty in anomaly location in traditional monitoring methods, thereby improving the intelligence level and response efficiency of power supply monitoring.

[0057] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0058] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0059] Figure 1 This is a flowchart illustrating an average power outage duration monitoring method based on an index lineage map, according to an exemplary embodiment.

[0060] Figure 2 This is a schematic diagram illustrating the specific process of a method for monitoring average power outage duration based on an index lineage map, according to an exemplary embodiment.

[0061] Figure 3 This is a structural block diagram of an average power outage duration monitoring device based on an index lineage map, according to an exemplary embodiment.

[0062] Figure 4 This is a diagram illustrating the internal structure of a computer device according to an exemplary embodiment. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0064] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure. The terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, method, product, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, product, or apparatus. Without further limitations, the presence of other identical or equivalent elements in a process, method, product, or apparatus that includes said elements is not excluded. For example, the use of terms such as "first," "second," etc., to denote names does not indicate any specific order.

[0065] In some embodiments of this disclosure, a method for monitoring average power outage duration based on an index lineage map is provided, such as... Figure 1 As shown, it includes the following steps:

[0066] S20. Continuously collect voltage signals from the low-voltage telemetry system, determine whether there are continuous low-voltage sections based on the voltage signals according to the preset threshold, and filter candidate power outage sections that meet the minimum duration by combining the sliding window algorithm.

[0067] Low-voltage telemetry systems typically refer to remote data acquisition and transmission systems used to monitor electrical parameters on the low-voltage side of distribution networks. They can continuously collect electrical parameters such as voltage, current, and power, and provide real-time feedback on equipment operating status and power supply quality, providing data support for power operation and maintenance, fault early warning, and energy consumption management.

[0068] The sliding window algorithm is a common data processing method for segmenting time-series data or continuous sequences. It involves continuously sliding a window of a fixed length across the data sequence to perform operations such as aggregation and filtering on the data within the window's coverage area. This enables structured extraction and interference removal of continuous data and is often used in scenarios such as signal denoising and event recognition.

[0069] Candidate power outage segments typically refer to continuous low-voltage time segments identified from voltage signals continuously collected by the low-voltage telemetry system. These segments are determined by a preset threshold and are selected through a sliding window algorithm. They meet the minimum duration set by the system and serve as the basic data unit for subsequent matching and verification with work order records.

[0070] S22. Match and verify the candidate power outage segments with the fault recovery records of the work order system to generate a standardized power outage event table containing start and end times and the area to which the power outage belongs.

[0071] Work order systems typically refer to digital management platforms used in the power operation and maintenance field for managing fault handling operations throughout the entire process. They enable the recording and transfer of information in stages such as power outage fault reporting, work order allocation, maintenance tracking, and recovery confirmation. They also accumulate fault recovery records containing key information such as fault location, handling time, and maintenance personnel. They are the core system connecting power supply operation and maintenance operations with data management.

[0072] Fault recovery records typically refer to structured information archives in the work order system that record the entire process of handling power outage faults. They include information such as the fault location, fault reporting time, fault type, dispatch information of maintenance personnel, on-site handling process, fault troubleshooting time, and confirmation of power restoration. These are core business data for verifying the authenticity of power outage events and clarifying the timeliness of fault handling.

[0073] The standardized power outage event table is a structured data table that is formed by matching and verifying candidate power outage segments with fault recovery records in the work order system. It contains key fields such as the start and end time and the region to which each power outage event belongs, providing a unified and standardized data foundation for indicator aggregation calculation.

[0074] S24. Calculate the average power outage duration index based on the standardized power outage event table, according to the specified region and time window.

[0075] Designated area and time window are the core spatiotemporal dimensions for statistical analysis of the average power outage duration index in distribution networks, forming the foundation for refined power supply monitoring. The designated area typically refers to a specific power supply space pre-divided according to the needs of distribution network operation and maintenance management, based on dimensions such as transformer substations, administrative regions, or power line coverage. It serves as the basic spatial unit for index statistics, ensuring accurate differentiation and comparison of power supply quality across different areas. The time window typically refers to a continuous time interval preset for dynamic index monitoring. It can be flexibly set according to dimensions such as hours, days, weeks, and months, serving as the basic time unit for index statistics and ensuring orderly traceability and analysis of power supply performance at different times. When combined, the system uses the designated area as the spatial boundary and the time window as the time range. It filters all power outage events within the corresponding range from a standardized power outage event table, and through aggregation calculation, obtains the average power outage duration index for that area within the corresponding time window, achieving spatiotemporal and refined monitoring and management of power supply quality.

[0076] Aggregate computing typically refers to a computational method that summarizes and processes multiple discrete data within a specific range. By integrating and calculating the data through preset statistical rules, it transforms scattered individual data into aggregated results with macroscopic statistical significance. It is the core processing method for realizing the transformation from detailed data to comprehensive indicators.

[0077] The average power outage duration index usually refers to the average value obtained by dividing the total duration of all power outage events in a specific area within a specified time window by the number of power outage events. It is a core indicator for measuring the continuity and reliability of power supply services and directly reflects the power supply quality and fault handling efficiency in the area.

[0078] S26. Construct a directed lineage map based on the average power outage duration index.

[0079] Directed lineage graphs typically refer to a traceability model for the entire process of indicator generation, constructed in the form of a directed graph. The core of this model is to treat the original data, processing logic, calculation rules, and final indicator related to the indicator as independent nodes. Directed edges are used to accurately represent the dependencies and data flow between nodes, clearly presenting the complete evolution path of the indicator from the data source to the final output, and realizing the visualization, traceability, and interpretability of the indicator generation process.

[0080] S28. Establish a dynamic baseline based on historical data, perform anomaly detection on real-time indicators, and when anomalies are detected, trace back to locate the root cause of the anomaly through the directed lineage map and generate diagnostic suggestions.

[0081] Dynamic baselines typically refer to dynamic reference standards built on historical indicator data that can adapt to natural fluctuations in the data. By integrating factors such as historical mean, standard deviation, and sensitivity parameters, they can adapt in real time to the normal fluctuation range of indicators under different scenarios, providing dynamically updated judgment criteria for accurately identifying indicator anomalies.

[0082] Real-time metrics typically refer to dynamic monitoring metrics generated by the system through real-time data collection and calculation at a preset frequency. They correspond to a specified area and the current time window, dynamically reflecting the average power outage duration under the current power supply status, and providing synchronous and accurate data support for anomaly detection and immediate operation and maintenance decisions.

[0083] Diagnostic recommendations typically refer to targeted operation and maintenance handling guidance plans generated after the system detects an abnormality in the average power outage duration indicator and completes root cause localization. These plans cover the explanation of the abnormality's root cause, priority handling directions, specific operation steps, and optimization suggestions, presented in a visual format to help operation and maintenance personnel quickly and accurately handle faults and optimize dispatch responses.

[0084] In some embodiments of this disclosure, a closed-loop management system for the average power outage duration indicator is implemented, encompassing data collection, event identification, and anomaly tracing. By integrating multi-source data and constructing a directed lineage graph, the system solves the problems of scattered data sources, opaque computational logic, and difficulty in locating anomalies in traditional monitoring methods, thereby improving the intelligence level and response efficiency of power supply monitoring.

[0085] The following is in conjunction with the appendix Figure 2 Please provide an explanation.

[0086] In some embodiments of this disclosure, S20 includes:

[0087] Construct a judgment function to identify continuous voltage segments where the voltage signal is below a preset threshold;

[0088] The judgment function outputs either 0 or 1; an output of 0 indicates normal operation, while an output of 1 indicates a possible low-voltage power outage.

[0089] In some implementations, voltage signals are continuously acquired from a low-voltage telemetry system. A power outage judgment function is constructed to analyze the voltage sample values ​​for each time period to determine whether a low-voltage power outage is possible. To avoid misjudgments caused by instantaneous voltage fluctuations, a sliding window algorithm is introduced to process the voltage signals and filter out continuous low-voltage segments that meet the system's minimum duration setting as candidate power outage segments. This process transforms continuous time-series voltage signals into structured event segments while effectively eliminating instantaneous fluctuation interference, ensuring the accuracy and stability of subsequent data processing.

[0090] In some examples, a conditional function can be constructed. The system identifies voltages below a threshold. The system extracts the voltage signal from the low-voltage telemetry system within a specified range and uses a sliding window algorithm to select candidate outage segments that meet the minimum duration requirement. This process transforms continuous time-series signals into structured event segments, laying the data foundation for subsequent event matching and index calculation. It also has the ability to remove transient fluctuation interference, ensuring the accuracy and stability of event extraction. In this stage, the system extracts the voltage signal from the low-voltage telemetry system. And based on a preset threshold, determine whether there is an abnormal low-voltage event. The power outage judgment function can be defined as follows (1):

[0091] (1)

[0092] in: This represents the voltage sample value at time t. This indicates the voltage threshold for determining a power outage. This indicates the result of a logical judgment: 1 indicates a possible low-voltage power outage, and 0 indicates normal operation.

[0093] To avoid misjudgment caused by instantaneous fluctuations, a sliding window aggregation method can be used to detect continuous low-pressure segments, as shown in the following formula (2):

[0094] (2)

[0095] in: This represents a candidate continuous low-pressure period. This indicates the minimum continuous duration set by the system. The purpose of this stage is to extract candidate time segments for suspected power outages from continuous voltage data and to prepare a preliminary data foundation for subsequent event verification and index calculation.

[0096] In some embodiments of this disclosure, by constructing a clear judgment function and combining it with a sliding window algorithm, candidate power outage segments are accurately identified, effectively avoiding misjudgments caused by instantaneous voltage fluctuations, ensuring the accuracy and reliability of power outage event identification, and providing high-quality basic data for subsequent data processing.

[0097] In some embodiments of this disclosure, S22 includes:

[0098] The candidate power outage segment is associated with the fault recovery record by regional identifier, and the degree of overlap in the time range of the candidate power outage segment and the fault recovery record is compared.

[0099] If the degree of overlap meets the preset matching conditions, the match is considered successful.

[0100] In some implementations, the extracted candidate power outage segments are associated and matched with fault recovery records in the work order system. By using region identifiers, the candidate power outage segments are bound to the corresponding region's fault recovery records, and the degree of overlap in their time ranges is further compared. When the overlap reaches a preset matching condition, the two are considered a successful match. The candidate power outage segments and their corresponding fault recovery records are then integrated into a complete power outage event, ultimately generating a standardized power outage event table containing key fields such as the start and end times and the region of each event. This process eliminates isolated or misjudged voltage fluctuation segments, achieving a semantic conversion from electrical signals to business events.

[0101] In some examples, an event set can be formed, as shown in equation (3):

[0102] (3)

[0103] in: This indicates the start time of the power outage for the i-th event. This represents the recovery completion time for the i-th event. This indicates the region or transformer area to which the event belongs. This stage involves matching the recovery timestamp with the work order system to eliminate abnormal short-term fluctuations or misidentified data, and abstracting the physical voltage data into a structured power outage event with clear business semantics, serving as the core data unit for subsequent indicator calculations.

[0104] In some embodiments of this disclosure, a matching verification method that associates regional identifiers with time range overlap is used to ensure the accurate correspondence between candidate power outage segments and fault recovery records, generating a standardized power outage event table that improves data consistency and effectiveness, and provides assurance for the accuracy of indicator calculation.

[0105] In some embodiments of this disclosure, S24 includes:

[0106] Based on the standardized power outage event table, the area and time range to be calculated are determined.

[0107] Calculate the duration of each power outage event in the standardized power outage event table;

[0108] The durations of all power outage events within the specified area and time range are aggregated to obtain the average power outage duration index for the corresponding area and time window.

[0109] In some implementations, the area and time window to be calculated are determined, and the duration of each power outage event is calculated one by one based on a standardized power outage event table. The durations of all power outage events within the specified area and time window are aggregated, and the average power outage duration index for that area within the corresponding time window is obtained by averaging. This transforms the discrete event data into a quantitative monitoring index with macroscopic reference significance.

[0110] In some examples, the average power outage duration within a given time window and region can be calculated based on a standardized event data table.

[0111] The formula for calculating the core indicators can be found in the following formula (4):

[0112] (4)

[0113] in: This represents the average power outage duration in region A within time window t. This indicates the number of power outage events in the area during that time period, with each item representing... This represents the duration of the i-th power outage. The significance of this step lies in transforming discrete event information into quantifiable monitoring metrics, which are crucial inputs for subsequent graph modeling and anomaly diagnosis.

[0114] In some embodiments of this disclosure, the indicators are aggregated and calculated according to a specified region and time window, which realizes flexible statistics of the average power outage duration indicator. This can accurately reflect the power supply service quality in different regions and time periods, and provide a quantitative basis for power supply dispatch optimization and service assessment.

[0115] In some embodiments of this disclosure, S26 includes:

[0116] Obtain all elements related to the average power outage duration indicator, including raw voltage data, power outage event identification logic, power outage event matching and verification logic, indicator aggregation calculation logic, and at least one of the average power outage duration indicators;

[0117] Treat each element as an independent node;

[0118] Based on the dependencies between the relevant elements, directed edges are used to connect the corresponding nodes to form a directed lineage graph;

[0119] The dependencies include the support relationship between the original voltage data and the power outage event identification logic, the input relationship between the power outage event identification results and the matching and verification logic, the supply relationship between the matching and verification power outage event data and the aggregation calculation logic, and the derivation relationship between the aggregation calculation logic and the average power outage duration index.

[0120] In some implementations, a comprehensive overview of all elements related to the average power outage duration metric is conducted, including raw voltage data, power outage event identification logic, matching and verification logic, aggregation calculation logic, and the final average power outage duration metric. Each type of element is designated as an independent node. Based on the actual dependencies between these elements—such as raw voltage data supporting the power outage event identification logic, identification results providing input for matching and verification, verified event data supplying data for aggregation calculation, and aggregation calculation deriving the final metric—directed edges are used to connect the corresponding nodes, constructing a complete directed lineage graph that clearly presents the entire dependency relationship in metric generation.

[0121] In some examples, a causal dependency graph can be constructed in the indicator generation process, in the form of a directed graph G = (V, E), where the set of nodes V includes: raw data nodes (such as voltmeters, power grid logs); and processing logic nodes (such as decision functions). Event identification function); aggregation calculation node (such as average function); output indicator node.

[0122] The edge set E represents the dependency between data and computation, for example, as shown in equation (5):

[0123] (5)

[0124] The core function of building a graph is to structure and visualize the entire process of data sources, processing logic, and indicator output, making the indicator generation path transparent and supporting upstream and downstream tracking and system diagnosis.

[0125] In some embodiments of this disclosure, the constructed directed lineage graph clearly presents the entire process dependency relationship of indicator generation, realizes bidirectional traceability from indicators to raw data and processing logic, enhances the transparency and interpretability of indicator calculation, and provides strong support for system diagnosis and maintenance.

[0126] In some embodiments of this disclosure, S28 includes:

[0127] Obtain historical operational data on the average power outage duration index, and establish a dynamic baseline based on the historical operational data;

[0128] The average power outage duration index is obtained through real-time calculation. The real-time index is compared with the dynamic baseline to determine whether there are any abnormalities in the real-time index.

[0129] If an anomaly in a real-time indicator is detected, the root cause of the anomaly is investigated by tracing back along the dependency path of the indicator generation based on the directed lineage graph.

[0130] Based on the identified root causes, targeted diagnostic recommendations are generated.

[0131] In some implementations, historical operational data on the average power outage duration index are collected, and a dynamic baseline is established based on this data. This baseline includes key elements such as the historical mean, historical standard deviation, and sensitivity parameters. The average power outage duration index, calculated in real time, is acquired and compared with the dynamic baseline. If the index value significantly exceeds the baseline range, it is determined that there is an abnormal fluctuation, and a warning state is marked, providing a trigger signal for subsequent anomaly tracing analysis.

[0132] In some examples, statistical modeling methods can be introduced to identify anomalies in the average power outage duration in real time. A dynamic baseline is established based on historical data, referring to the following formula (6):

[0133] (6)

[0134] in: This represents the average value of region A within a historical time window. Indicates historical standard deviation, This represents the sensitivity parameter. The model can dynamically adapt to the natural fluctuations in power outage duration across different regions, accurately capturing abnormal jumps and providing data trigger signals for system tracing.

[0135] In some embodiments of this disclosure, the dynamic baseline established based on historical data can adapt to the fluctuation differences in different regions, improving the accuracy of anomaly detection. Combined with the backtracking mechanism of the directed lineage map, it enables rapid location of the root cause of the anomaly and automatic generation of diagnostic suggestions, shortening the fault response time and improving the efficiency of operation and maintenance services.

[0136] This disclosure provides several methods for monitoring average power outage duration based on indicator lineage graphs. These methods achieve closed-loop management of the average power outage duration indicator throughout the entire process, from data collection and event identification to anomaly tracing. By integrating multi-source data and constructing directed lineage graphs, these methods solve the problems of scattered data sources, opaque calculation logic, and difficulty in locating anomalies in traditional monitoring methods, thereby improving the intelligence level and response efficiency of power supply monitoring.

[0137] It is understood that the various embodiments of the methods described in this specification are presented in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. Related details can be found in the descriptions of other method embodiments.

[0138] It should be understood that although the steps in the flowcharts shown in the accompanying drawings are displayed sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the accompanying drawings may include multiple steps or stages, which are not necessarily completed at the same time, but may be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but may be performed alternately or in turn with other steps or at least a portion of the steps or stages of other steps.

[0139] Based on the description of the above-described embodiments of the average power outage duration monitoring method based on indicator lineage graphs, this disclosure also provides an average power outage duration monitoring device based on indicator lineage graphs for implementing the above-described average power outage duration monitoring method based on indicator lineage graphs. The device may include a system (including a distributed system), software (application), module, component, controller, server, terminal, etc., using the method described in the embodiments of this specification, combined with necessary hardware implementation. Based on the same innovative concept, the devices in one or more embodiments provided in this disclosure are as described in the following embodiments. Since the implementation schemes and methods for solving the problem by the devices are similar, the implementation of specific devices in the embodiments of this specification can refer to the implementation of the aforementioned method, and repeated details will not be repeated. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0140] Figure 3 This is a schematic block diagram illustrating an average power outage duration monitoring device based on an indicator lineage graph, according to an exemplary embodiment. The device can be the aforementioned terminal, a server, or a module, component, device, control unit, etc., integrated into the terminal. For details, please refer to... Figure 3The device 100 may include: a first module 120, a second module 140, a third module 160, a fourth module 180, and a fifth module 190. The first module 120 is used to continuously acquire voltage signals from a low-voltage telemetry system, determine whether there are continuous low-voltage sections based on the voltage signals using a preset threshold, and filter candidate outage sections that meet the minimum duration using a sliding window algorithm. The second module 140 is used to match and verify the candidate outage sections with fault recovery records from a work order system, generating a standardized outage event table containing start and end times and the region to which they belong. The third module 160 is used to aggregate and calculate an average outage duration index based on the standardized outage event table according to a specified region and time window. The fourth module 180 is used to construct a directed lineage graph based on the average outage duration index. The fifth module 190 is used to establish a dynamic baseline based on historical data, perform anomaly detection on real-time indicators, and, when an anomaly is detected, trace back to locate the root cause of the anomaly using the directed lineage graph and generate diagnostic suggestions.

[0141] The modules in the aforementioned average power outage duration monitoring device based on indicator lineage maps can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0142] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 4 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a method for monitoring average power outage duration based on an indicator lineage graph.

[0143] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0144] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer device, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, implements the average power outage duration monitoring method based on index lineage maps as described in any embodiment of this specification.

[0145] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer-readable storage medium that, when the instructions in the computer-readable storage medium are executed by the processor of a computer device, enables the computer device to implement the average power outage duration monitoring method based on index lineage maps as described in any embodiment of this disclosure.

[0146] Based on the foregoing description of the relevant methods and apparatus embodiments, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the average power outage duration monitoring method based on index lineage maps as described in any embodiment of this specification.

[0147] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on its differences from other embodiments. In particular, hardware + program embodiments are relatively simple in description because they are fundamentally similar to method embodiments; relevant parts can be referred to the descriptions in the method embodiments.

[0148] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0149] It should be noted that the apparatus, computer equipment, storage medium, and computer program products described above may also include other implementation methods according to the description of the method embodiments. Specific implementation methods can be found in the description of the relevant method embodiments. Furthermore, new embodiments formed by combinations of features from various methods, apparatuses, devices, and server embodiments still fall within the scope of this disclosure and will not be elaborated upon here.

[0150] For ease of description, the above devices are described in terms of function, divided into various modules. Of course, when implementing one or more of these specifications, the functions of each module can be implemented in the same or different software and / or hardware, or a module that performs the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling and communication connections between the devices or units shown or described can be implemented through direct and / or indirect coupling / connection, through standard or custom interfaces or protocols, and can be implemented electrically, mechanically, or in other forms.

[0151] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0152] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope.

Claims

1. A method for monitoring average power outage duration based on an index lineage map, characterized in that, The method includes: Voltage signals are continuously collected from the low-voltage telemetry system. A preset threshold is used to determine whether there are continuous low-voltage sections based on the voltage signals. A sliding window algorithm is then used to filter candidate power outage sections that meet the minimum duration. The candidate power outage segments are matched and verified with the fault recovery records of the work order system to generate a standardized power outage event table that includes start and end times and the area to which the outage belongs. The average power outage duration index is calculated by aggregating and calculating based on the standardized power outage event table according to the specified region and time window. A directed lineage map is constructed based on the average power outage duration index; A dynamic baseline is established based on historical data, and anomalies are detected in real-time indicators. When anomalies are detected, the root cause of the anomaly is located by tracing back upwards through the directed lineage map, and diagnostic suggestions are generated.

2. The method according to claim 1, characterized in that, The process of continuously acquiring voltage signals from a low-voltage telemetry system, determining the existence of continuous low-voltage sections based on preset thresholds, and filtering candidate power outage sections that meet the minimum duration using a sliding window algorithm includes: Construct a judgment function to identify continuous voltage segments where the voltage signal is below a preset threshold; The judgment function outputs either 0 or 1; an output of 0 indicates normal operation, while an output of 1 indicates a possible low-voltage power outage.

3. The method according to claim 1, characterized in that, The step of matching and verifying the candidate power outage segments with the fault recovery records of the work order system to generate a standardized power outage event table containing start and end times and the region to which the event belongs includes: The candidate power outage segment is associated with the fault recovery record by regional identifier, and the degree of overlap in the time range of the candidate power outage segment and the fault recovery record is compared. If the degree of overlap meets the preset matching conditions, the match is considered successful.

4. The method according to claim 1, characterized in that, The step of aggregating and calculating the average power outage duration index based on the standardized power outage event table according to the specified region and time window includes: Based on the standardized power outage event table, the area and time range to be calculated are determined. Calculate the duration of each power outage event in the standardized power outage event table; The durations of all power outage events within the specified area and time range are aggregated to obtain the average power outage duration index for the corresponding area and time window.

5. The method according to claim 1, characterized in that, The construction of the directed lineage map based on the average power outage duration index includes: Obtain all elements related to the average power outage duration indicator, including raw voltage data, power outage event identification logic, power outage event matching and verification logic, indicator aggregation calculation logic, and at least one of the average power outage duration indicators; Treat each element as an independent node; Based on the dependencies between the relevant elements, directed edges are used to connect the corresponding nodes to form a directed lineage graph; The dependencies include the support relationship between the original voltage data and the power outage event identification logic, the input relationship between the power outage event identification results and the matching and verification logic, the supply relationship between the matching and verification power outage event data and the aggregation calculation logic, and the derivation relationship between the aggregation calculation logic and the average power outage duration index.

6. The method according to claim 1, characterized in that, The process involves establishing a dynamic baseline based on historical data, detecting anomalies in real-time indicators, and, upon detecting anomalies, tracing back to the root cause of the anomaly using the directed kinship map to generate diagnostic suggestions, including: Obtain historical operational data on the average power outage duration index, and establish a dynamic baseline based on the historical operational data; The average power outage duration index is obtained through real-time calculation. The real-time index is compared with the dynamic baseline to determine whether there are any abnormalities in the real-time index. If an anomaly in a real-time indicator is detected, the root cause of the anomaly is investigated by tracing back along the dependency path of the indicator generation based on the directed lineage graph. Based on the identified root causes, targeted diagnostic recommendations are generated.

7. A device for monitoring the average power outage duration based on an index lineage map, characterized in that, The device includes: The first module is used to continuously acquire voltage signals from the low-voltage telemetry system, determine whether there are continuous low-voltage sections based on the voltage signals according to a preset threshold, and filter candidate power outage sections that meet the minimum duration by combining a sliding window algorithm. The second module is used to match and verify the candidate power outage segments with the fault recovery records of the work order system, and generate a standardized power outage event table that includes start and end times and the area to which the outage belongs. The third module is used to aggregate and calculate the average power outage duration index based on the standardized power outage event table according to the specified area and time window. The fourth module is used to construct a directed lineage map based on the average power outage duration index; The fifth module is used to establish a dynamic baseline based on historical data, detect anomalies in real-time indicators, and, when an anomaly is detected, trace back to locate the root cause of the anomaly through the directed lineage map and generate diagnostic suggestions.

8. A computer device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1 to 6.

Images