Data analysis-based automatic power distribution equipment setting management method and system

Abstract

The application discloses an automatic power distribution equipment setting value management method and system based on data analysis, and belongs to the technical field of data analysis. The system comprises a dynamic sensing module, an abnormality analysis module, a computing power allocation module and a setting value management module; the dynamic sensing module is used for collecting GIS maps and environmental parameters in a coverage area and operation parameters of each power distribution equipment; the abnormality analysis module is used for setting a typhoon entity on the GIS map, predicting the scale and behavior, screening the power distribution equipment, calculating an abnormality index and setting an abnormal equipment; the computing power allocation module is used for predicting a time period during which the typhoon entity passes each abnormal equipment, dividing overlapping time periods and setting time points; analyzing computing power allocation ratios of each abnormal equipment at the time points, and making the computing power allocation ratios form a smooth gradient in a continuous time period; and the setting value management module calculates a computing power quota according to the computing power allocation ratios, so as to set a refresh frequency and resolution of a fault rehearsal engine when the abnormal equipment is running, and adjust the setting value of each protection unit in real time.

Description

Technical Field

[0001] This invention relates to the field of data analysis technology, specifically to a method and system for setting management of automated power distribution equipment based on data analysis. Background Technology

[0002] In power systems, the distribution network serves as the final link in power transmission, and the safe operation of distribution equipment directly impacts power supply reliability. Especially during extreme typhoon weather, the rapid movement of typhoons brings drastic changes in environmental parameters such as strong winds, torrential rain, and temperature and humidity, which can impact the insulation, heat dissipation, and mechanical structure of distribution equipment, altering its fault characteristics and resilience. Traditional protection settings are based on static operating condition designs, making it difficult to adapt to these dynamic environmental changes in real time. This results in distribution equipment protection units being unable to effectively respond to abnormal conditions, thus triggering potential faults or power outage risks.

[0003] Currently, traditional setting management methods for power distribution equipment have significant shortcomings in responding to typhoon impacts. On one hand, they lack the ability to perform refined analysis and prediction of dynamic changes in environmental parameters, failing to accurately quantify the contribution of environmental parameter fluctuations to specific protection units. This results in coarse risk identification and a failure to focus maintenance resources on high-threat power distribution equipment. On the other hand, rigid computing resource allocation prevents dynamic adjustment of allocation strategies when typhoon movement leads to overlapping computing demands across multiple devices. Furthermore, the fixed parameters of the fault simulation engine cannot adapt to changes in computing power, limiting the flexibility to improve simulation accuracy during high-risk periods. Simultaneously, protection setting adjustment schemes rely on simple threshold rules, failing to fully utilize real-time data correlation analysis and iterative optimization strategies. This leads to a disconnect between the scheme and environmental evolution, making it difficult to generate accurate dynamic setting adjustment strategies to meet the needs of extreme operating conditions. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for setting management of automated power distribution equipment based on data analysis, so as to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides a data analysis-based method for setting management of automated power distribution equipment, comprising:

[0006] S100 collects GIS maps and global environmental parameters within the coverage area, as well as the operating parameters of each power distribution device.

[0007] The coverage area refers to the physical area jointly covered by the power distribution network and power distribution equipment.

[0008] By using sensor networks and Doppler weather radar technology, the continuous distribution of various environmental parameters in the airspace within the coverage area is monitored. Global environmental parameters refer to the basic physical quantities that reflect the environmental state within the coverage area.

[0009] Radar monitoring enables continuous spatial distribution of atmospheric conditions, while sensor networks collect equipment-level parameters at fixed points. Together, they form a dual coverage of "airspace + location".

[0010] Power distribution equipment refers to the equipment in a power system that converts medium voltage to low voltage and distributes electrical energy, and includes different protection units. A protection unit is an independent module within the power distribution equipment that has preset electrical quantity settings and operating logic.

[0011] Each protection unit has a set value and an electrical quantity. By comparing the difference between the real-time electrical quantity and the preset set value, the protection and isolation function for overcurrent or short circuit faults is performed.

[0012] Operating parameters include local environmental parameters at the location of the power distribution equipment, as well as the settings and electrical quantities of each protection unit within it. The types and quantities of global and local environmental parameters are completely identical.

[0013] The global and local environmental parameters use the exact same types and quantities to ensure horizontal data comparability.

[0014] Construct a real-time, integrated environmental and equipment data monitoring network. By deploying a sensor network and Doppler weather radar, synchronously collect GIS geographic information of the coverage area, global environmental parameters, and local environmental parameters and protection unit operating parameters of each power distribution device. This provides a high-precision, highly consistent data base for subsequent analysis, eliminating benchmark drift caused by differences in data sources.

[0015] S200: Analyze environmental and operational parameters, define the typhoon entity on the GIS map, and predict its size and behavior. After screening all power distribution equipment, calculate the anomaly index and designate abnormal equipment based on the anomaly index.

[0016] S200 includes:

[0017] S201. Using the WRF meteorological model, the atmospheric state is simulated and analyzed based on global environmental parameters within the coverage area, and the core location and coverage area of ​​the typhoon entity are identified and marked on the GIS map.

[0018] S202. Based on local environmental parameters at the location of power distribution equipment, Kalman filter data fusion technology is used to refine the core location and coverage boundary of the typhoon entity and improve spatial resolution.

[0019] S203. Using a spatiotemporal trajectory prediction model based on a long short-term memory network, predict the duration of the typhoon based on refined typhoon parameters. The spatiotemporal evolution trajectory of the internal movement path.

[0020] The WRF model is used to invert the atmospheric state from global environmental parameters to generate the initial state of the typhoon.

[0021] Kalman filtering is used to fuse local environmental parameters of power distribution equipment to improve boundary resolution.

[0022] LSTM spatiotemporal trajectory model prediction duration The internal movement path ensures that the trajectory accuracy decreases controllably with the prediction time.

[0023] S204. Mark the location of each power distribution device on the GIS map, analyze the evolution of the coverage area as the typhoon moves according to its spatiotemporal evolution trajectory, and filter out all power distribution devices within the evolution area.

[0024] Evolutionary region refers to the duration The continuous area covered by an internal typhoon as it moves along its spatiotemporal evolution trajectory.

[0025] S205. Predict the time period during which the typhoon will pass through each power distribution equipment, analyze the changes in environmental parameters within the typhoon's coverage area during the time period at each power distribution equipment, and calculate the first coefficient of each environmental parameter. Specifically, this includes:

[0026] S2051. Predicting the changes in the coverage area of ​​a typhoon as it moves according to its spatiotemporal evolution trajectory, and the distribution equipment... Time when the location was included in the coverage area and time out of coverage The combination is a time period.

[0027] S2052. Analyze the changes in environmental parameters within the typhoon's coverage area during the analysis period, and pre-set weighting coefficients for each environmental parameter. Substitute these values ​​into the formula to calculate the first coefficient of each environmental parameter:

[0028] ;

[0029] In the formula, These are the extreme values ​​of environmental parameters within a time period. This represents the average value of environmental parameters over a given time period.

[0030] The first coefficient is used to describe the relative fluctuation range of the extreme values ​​and average values ​​of environmental parameters during the typhoon's impact period. This calculation reflects the degree of abnormal fluctuation of the parameter during the typhoon's passage and introduces a preset weight to amplify the abnormal contribution value of key parameters.

[0031] Weighting coefficient The extreme value ratio reflects the importance of the parameter, while the extreme value ratio reflects the intensity of parameter mutation.

[0032] S2053, and so on, calculate the first coefficient of each environmental parameter based on the time period analysis of the location of each power distribution equipment.

[0033] S206, Count the number of all environmental parameters. Based on the operating parameters, a fitting relationship expression is generated for each protection unit in each power distribution device. Combined with the first coefficient, the abnormality index of the corresponding power distribution device is calculated, and abnormal devices are designated. Specifically, this includes:

[0034] S2061, Obtaining power distribution equipment The operating parameters were analyzed, along with local environmental parameters and protection units at different historical moments. The set values ​​and electrical quantities are for the protection unit. The fitting yields the relational expression. Specifically, this includes:

[0035] S2061-1 Analysis of power distribution equipment The operating parameters are set evenly. Each historical moment. Analyzing protection units at the same historical moment. constant value and electrical quantities Substitute into the formula to calculate the influence coefficient at each historical moment. :

[0036] ;

[0037] In the formula, A constant greater than 1 This is the attenuation coefficient.

[0038] The influence coefficient is used to measure the degree of deviation between the protection unit setting value and the electrical quantity. The electrical quantity deviation is converted into a standardized influence index through an exponential decay function.

[0039] When the deviation decreases, the calculation result approaches the theoretical extreme value, which intuitively represents the abnormality of the equipment's operating status.

[0040] S2061-2. Using the influence coefficients at the same historical moment as the dependent variable, and all local environmental parameters as independent variables, package them into a sample. Establish a linear regression model and set the intercept. and regression coefficients .

[0041] S2061-3, This Each sample is input into a linear regression model for training, with the independent variable in each sample serving as the input value. Output value The difference between the dependent variable and the differential variable is used as the difference coefficient. The expression is as follows:

[0042] ;

[0043] S2061-4. Adjust the intercept and regression coefficients until the sum of the difference coefficients of all samples is minimized, thus obtaining the trained protection unit. Relational expressions.

[0044] A mathematical mapping relationship between environmental parameters and influence coefficients is established. By fitting and training multiple sets of historical data, the linear influence weight of changes in each environmental parameter on the abnormal state of the protected unit is quantified, providing a basis for subsequent anomaly assessment.

[0045] S2062, Computational Protection Unit The sum of all regression coefficients in the relational expression Divide the regression coefficients corresponding to each environmental parameter by 1 / 2. Receive protection unit The second coefficient of each of the following environmental parameters .

[0046] S2063, respectively, power distribution equipment The fitting relationship expressions for each of the other protection units are determined, and the second coefficients of each environmental parameter under each protection unit are calculated.

[0047] S2064. Calculate the anomaly coefficient of each protection unit based on the first coefficient and the second coefficient. Anomaly coefficients of all protection units Summation as a power distribution device Abnormal index The formula for calculating the anomaly coefficient is as follows:

[0048] ;

[0049] In the formula, For the first The second coefficient of the environmental parameter, For the first The first coefficient of the environmental parameter, This is the sum of the first coefficients of all environmental parameters.

[0050] By combining the weight of the impact of individual environmental parameters on the protection unit with the degree of abnormal fluctuation during typhoons, the comprehensive abnormal risk level of the protection unit under severe environment is quantified through weighted ratio calculation.

[0051] S2065. Calculate the abnormality index of each power distribution device, and classify the power distribution devices with an abnormality index greater than the threshold as abnormal devices.

[0052] This system enables accurate identification and quantitative assessment of vulnerable power distribution equipment during typhoons. A typhoon evolution model is constructed through meteorological simulation, data fusion, and trajectory prediction. Combined with the electrical response characteristics of protection units and spatiotemporal coupling analysis, a dynamic anomaly index is generated, effectively screening high-risk power distribution equipment and avoiding resource waste on low-risk targets.

[0053] S300, predicting the time periods of typhoon entity passing through various anomalous devices, dividing overlapping time periods and setting time points. Analyzing the computing power allocation of each anomalous device at each time point, and ensuring the computing power allocation forms a smooth gradient over continuous time periods. Specifically, this includes:

[0054] S301. Analyze whether the time periods of each abnormal device overlap, and divide the duration of each abnormal device into fixed and non-unique periods as overlapping time periods. The abnormal devices corresponding to adjacent overlapping time periods are not completely the same.

[0055] Adjacent overlapping time periods refer to two overlapping areas whose first and last digits are connected, not two adjacent overlapping time periods with a certain time interval.

[0056] S302, Setting Duration Divide the duration of each overlapping period by . The sample counts for each device are obtained. Within each overlapping time period, time points are evenly distributed according to the sample count, and the computing power allocation of all abnormal devices at each time point is analyzed. Specifically, this includes:

[0057] S3021, predicted typhoon body at the specified time point Substitute the various environmental parameters within the coverage area into the abnormal equipment. The expected influence coefficient of each protection unit is calculated from the relational expression of each protection unit.

[0058] S3022. Obtain the abnormality coefficient of each protection unit under the abnormal equipment, and calculate the abnormal equipment separately based on the expected impact coefficient. Allocation coefficient :

[0059] ;

[0060] In the formula, Abnormal equipment The total number of all protection units in the system. and The first The abnormality coefficient and expected impact coefficient of each protection unit.

[0061] S3023. Similarly, calculate the allocation coefficient for each abnormal device, and sum the allocation coefficients of all abnormal devices as the allocation index.

[0062] S3024. Divide the allocation coefficient of each abnormal device by the allocation index to obtain its respective computing power allocation ratio. Calculate the computing power allocation ratio of each abnormal device at each time point.

[0063] S303, Predicting Duration The duration of a single abnormal device within a timeframe that is not overlapping is considered an exclusive timeframe, while the duration of a timeframe that is neither overlapping nor exclusive is considered an idle timeframe.

[0064] Overlapping periods represent periods when multiple faulty devices coexist, and computing power is allocated according to their importance. Exclusive periods represent periods when only a single faulty device is affected, and 100% computing power is allocated to them. Idle periods represent periods when no faulty devices are affected, and no computing power is allocated to them.

[0065] S304. Set the computing power ratio to 0 during idle periods and set the computing power ratio to 100% for abnormal devices during exclusive periods.

[0066] S305. Perform a smoothing operation on the computing power allocation of all abnormal devices at each time point within the overlapping period, as well as the computing power allocation of abnormal devices corresponding to idle and exclusive periods.

[0067] S306. By constraining the jump variables in computing power allocation between adjacent time points through time series analysis, the computing power allocation values ​​of all abnormal devices in continuous time periods form a gradient approach process without sudden changes along the time axis.

[0068] A time-window-based elastic computing power allocation strategy is constructed. By modeling time-slicing and allocation coefficients, computing resources are scheduled on demand during the typhoon's evolution, and smooth gradient constraints are used to eliminate sudden changes in computing power, ensuring the continuous and stable execution of computing tasks.

[0069] S400 calculates the allocated computing power for each faulty device at different times based on the computing power allocation ratio, sets the refresh rate and resolution of the fault prediction engine based on the computing power allocation, and dynamically adjusts the setpoints for each protection unit. Specifically, this includes:

[0070] S401. Based on the time-varying supply capacity of the total computing resource pool and the computing power ratio of each abnormal device, the total computing power is allocated to each fault simulation task in a proportional relationship, and the available computing power quota for each abnormal device is generated. This quota represents the maximum amount of computing resources that can be consumed within the corresponding time window.

[0071] S402. Adjusting the computing power allocation affects the operation configuration of the fault simulation engine. Increasing the computing power allocation increases the number of simulation steps per unit time and refines the mesh generation accuracy. Decreasing the computing power allocation reduces the simulation iteration frequency and coarsens the model's order reduction scale.

[0072] Under the constraint of limited computing power, the S403 fault prediction engine combines real-time collected environmental parameters and generates protection setting adjustment schemes that adapt to the evolution of harsh environments through time-series iterative optimization strategies, and sends them to the corresponding protection units in real time.

[0073] Highly adaptive protection setting optimization is achieved under limited computing power constraints. Dynamic mapping between computing power and pre-simulation engine configuration enables flexible adjustment of simulation accuracy. The optimal setting scheme is generated iteratively by combining real-time environmental parameters, significantly improving the reliability of power distribution equipment protection under severe weather conditions.

[0074] The present invention also provides an automated power distribution equipment setting management system based on data analysis, including a dynamic sensing module, an anomaly analysis module, a computing power allocation module, and a setting management module.

[0075] The dynamic sensing module is used to collect GIS maps and environmental parameters within the coverage area, as well as the operating parameters of each power distribution device.

[0076] The sensor network collects GIS map information, global environmental parameters, and operating parameters of each power distribution device in real time within the coverage area, while ensuring that the types and quantities of parameters are consistent.

[0077] It provides basic data support to achieve comprehensive and real-time perception of the environment and equipment status, laying the data foundation for subsequent typhoon forecasting and anomaly detection, reducing human intervention errors and improving data accuracy, thereby improving the system's response speed and initialization reliability.

[0078] The anomaly analysis module is used to set typhoon entities on GIS maps and predict their size and behavior, and to calculate anomaly indices and set abnormal equipment after screening power distribution equipment.

[0079] Typhoon entities are set on GIS maps, and the size and path of typhoons are predicted using WRF meteorological models and Kalman filter data fusion technology. Anomalies in power distribution equipment are calculated by combining long short-term memory spatiotemporal trajectory models and linear regression analysis, thereby screening out abnormal equipment.

[0080] Accurately identify vulnerable power distribution equipment affected by typhoons, optimize resource allocation, reduce computational redundancy, and improve prediction accuracy by dynamically fitting relational expressions, thereby enhancing proactive early warning capabilities and decision-making efficiency under severe weather conditions.

[0081] The computing power allocation module is used to predict the time period during which the typhoon entity passes through various abnormal devices, divide overlapping time periods, and set time points. It analyzes the computing power allocation ratio of each abnormal device at each time point and makes the computing power allocation ratio form a smooth gradient over continuous time periods.

[0082] The system predicts the time period during which the typhoon entity passes through various anomalous devices, divides the time period into overlapping and exclusive periods, calculates the allocation coefficient at each time point, and then performs a smoothing operation to form a smooth gradient of computing power allocation without abrupt changes within consecutive time periods.

[0083] Dynamically optimize the allocation of computing resources to avoid waste of computing resources, ensure that computing tasks flow efficiently in continuous time periods, improve system computing efficiency and reduce the risk of interruption, and provide stability assurance for setpoint management.

[0084] The setting management module calculates the computing power quota based on the computing power allocation ratio, thereby setting the refresh frequency and resolution of the fault prediction engine for abnormal equipment operation, and adjusting the setting value in real time for each protection unit.

[0085] The computing power quota is calculated based on the computing power allocation ratio, the operation configuration of the fault simulation engine is dynamically adjusted, and the protection setting adjustment scheme is generated in combination with real-time environmental parameters. The scheme is then distributed to the protection unit in real time through a time-series iterative optimization strategy.

[0086] By achieving dynamic adaptive adjustment of protection settings under limited computing power constraints, the response accuracy and reliability under disasters such as typhoons can be improved, the risk of equipment failure can be reduced, and the resource utilization rate can be optimized, ultimately enhancing the overall safety and robustness of the power distribution system.

[0087] Compared with the prior art, the beneficial effects achieved by the present invention are:

[0088] Dynamic Environmental Adaptability: This solution can respond in real time to dynamic changes in extreme weather such as typhoons. By collecting environmental parameters and power distribution equipment operating parameters of the coverage area, it analyzes typhoon paths and equipment risks, and dynamically generates protection setting adjustment schemes. Compared with existing technologies, it solves the problem of rigid protection settings caused by fluctuations in environmental parameters, enabling equipment to quickly adapt to changes in parameters such as wind speed, pollution levels, temperature, and humidity, thus improving the resilience and stability of power distribution equipment in harsh environments.

[0089] Refined Risk Identification and Resource Focus: This solution accurately quantifies the contribution of power distribution equipment to typhoon-related risks by calculating the primary and secondary coefficients of environmental parameters and the anomaly index of power distribution equipment, thus identifying high-threat abnormal equipment. This avoids the crude risk assessment problems of existing technologies and allows for optimized focus of maintenance resources on the most vulnerable power distribution equipment and its protection units, thereby improving maintenance efficiency and power supply reliability.

[0090] Adaptive computing power allocation and engine optimization: Based on the overlapping time period analysis of typhoon movement trajectories, this scheme dynamically sets the computing power ratio of each abnormal device to form a smooth gradient change. Simultaneously, by adjusting the refresh rate and resolution of the fault simulation engine through computing power allocation, simulation accuracy is improved during critical periods. Compared to the static resource allocation and fixed operating parameters of existing technologies, this method achieves flexible allocation and maximum utilization of computing power resources, reduces resource waste, and ensures high-precision protection setting adjustments.

[0091] Integrated Data Processing and Rapid Response: This solution integrates GIS mapping, environmental parameter collection, equipment operation analysis, and real-time setting issuance processes. Through linear regression models and iterative optimization strategies, it achieves end-to-end management from data acquisition to protection setting adjustment. Existing technologies lack this linkage mechanism, leading to a disconnect between adjustment plans and environmental evolution. This solution addresses this issue, ensuring that abnormal equipment can quickly receive optimization instructions under typhoon conditions, reducing the risk of power outages. Attached Figure Description

[0092] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0093] Figure 1 This is a flowchart illustrating the automated power distribution equipment setpoint management method based on data analysis according to the present invention.

[0094] Figure 2 This is a schematic diagram of the structure of the automated power distribution equipment setting management system based on data analysis according to the present invention. Detailed Implementation

[0095] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0096] Example 1: Please refer to Figure 1 This invention provides a data analysis-based method for setting management of automated power distribution equipment, comprising:

[0097] S100 collects GIS maps and global environmental parameters within the coverage area, as well as the operating parameters of each power distribution device.

[0098] The coverage area refers to the physical area jointly covered by the power distribution network and power distribution equipment.

[0099] By using sensor networks and Doppler weather radar technology, the continuous distribution of various environmental parameters in the airspace within the coverage area is monitored. Global environmental parameters refer to the basic physical quantities that reflect the environmental state within the coverage area.

[0100] In practice, radar monitoring enables continuous spatial distribution of atmospheric conditions, while sensor networks collect equipment-level parameters at fixed points. Together, they form a dual coverage of "airspace + location".

[0101] Power distribution equipment refers to the equipment in a power system that converts medium voltage to low voltage and distributes electrical energy, and includes different protection units. A protection unit is an independent module within the power distribution equipment that has preset electrical quantity settings and operating logic.

[0102] Each protection unit has a set value and an electrical quantity. By comparing the difference between the real-time electrical quantity and the preset set value, the protection and isolation function for overcurrent or short circuit faults is performed.

[0103] Operating parameters include local environmental parameters at the location of the power distribution equipment, as well as the settings and electrical quantities of each protection unit within it. The types and quantities of global and local environmental parameters are completely identical.

[0104] In the specific implementation process, the global and local environmental parameters are exactly the same in type and quantity (such as including wind speed, pollution level, temperature and humidity) to ensure the horizontal comparability of data.

[0105] Construct a real-time, integrated environmental and equipment data monitoring network. By deploying a sensor network and Doppler weather radar, synchronously collect GIS geographic information of the coverage area, global environmental parameters (such as wind speed, pollution level, temperature and humidity), and local environmental parameters of each power distribution device and operating parameters of protection units (set values, electrical quantities), providing a high-precision and highly consistent data base for subsequent analysis and eliminating the benchmark drift problem caused by differences in data sources.

[0106] S200: Analyze environmental and operational parameters, define the typhoon entity on the GIS map, and predict its size and behavior. After screening all power distribution equipment, calculate the anomaly index and designate abnormal equipment based on the anomaly index.

[0107] S200 includes:

[0108] S201. The WRF (Weather Research and Forecasting) meteorological model is used to simulate and analyze the atmospheric state based on global environmental parameters within the coverage area, and the core location and coverage area of ​​the typhoon entity are identified and marked on the GIS map.

[0109] S202. Based on local environmental parameters at the location of power distribution equipment, Kalman filter data fusion technology is used to refine the core location and coverage boundary of the typhoon entity and improve spatial resolution.

[0110] S203. Using a spatiotemporal trajectory prediction model based on a long short-term memory network, predict the duration of the typhoon based on refined typhoon parameters. The spatiotemporal evolution trajectory of the internal movement path.

[0111] In the specific implementation process, the WRF model is used to invert the atmospheric state from global environmental parameters to generate the initial state of the typhoon (core location, coverage area).

[0112] Kalman filtering can be used to integrate local environmental parameters of power distribution equipment to improve boundary resolution (such as optimizing the accuracy of typhoon radius from the kilometer level to the hundred-meter level).

[0113] LSTM spatiotemporal trajectory model prediction duration The internal movement path ensures that the trajectory accuracy decreases controllably with the prediction time.

[0114] S204. Mark the location of each power distribution device on the GIS map, analyze the evolution of the coverage area as the typhoon moves according to its spatiotemporal evolution trajectory, and filter out all power distribution devices within the evolution area.

[0115] In the specific implementation process, the evolution zone refers to the duration. The continuous area covered by an internal typhoon as it moves along its spatiotemporal evolution trajectory.

[0116] S205. Predict the time period during which the typhoon will pass through each power distribution equipment, analyze the changes in environmental parameters within the typhoon's coverage area during the time period at each power distribution equipment, and calculate the first coefficient of each environmental parameter. Specifically, this includes:

[0117] S2051. Predicting the changes in the coverage area of ​​a typhoon as it moves according to its spatiotemporal evolution trajectory, and the distribution equipment... Time when the location was included in the coverage area and time out of coverage The combination is a time period.

[0118] S2052. Analyze the changes in environmental parameters within the typhoon's coverage area during the analysis period, and pre-set weighting coefficients for each environmental parameter. Substitute these values ​​into the formula to calculate the first coefficient of each environmental parameter:

[0119] ;

[0120] In the formula, These are the extreme values ​​of environmental parameters within a time period. This represents the average value of environmental parameters over a given time period.

[0121] The first coefficient is used to describe the relative fluctuation range of the extreme values ​​and average values ​​of environmental parameters during the typhoon's impact period. This calculation reflects the degree of abnormal fluctuation of the parameter during the typhoon's passage and introduces a preset weight to amplify the abnormal contribution value of key parameters.

[0122] In the specific implementation process, the weighting coefficient The extreme value ratio reflects the importance of parameters (e.g., wind speed weight > temperature and humidity), while the extreme value ratio reflects the intensity of parameter abrupt changes.

[0123] S2053, and so on, calculate the first coefficient of each environmental parameter based on the time period analysis of the location of each power distribution equipment.

[0124] S206, Count the number of all environmental parameters. Based on the operating parameters, a fitting relationship expression is generated for each protection unit in each power distribution device. Combined with the first coefficient, the abnormality index of the corresponding power distribution device is calculated, and abnormal devices are designated. Specifically, this includes:

[0125] S2061, Obtaining power distribution equipment The operating parameters were analyzed, along with local environmental parameters and protection units at different historical moments. The set values ​​and electrical quantities are for the protection unit. The fitting yields the relational expression. Specifically, this includes:

[0126] S2061-1 Analysis of power distribution equipment The operating parameters are set evenly. Each historical moment. Analyzing protection units at the same historical moment. constant value and electrical quantities Substitute into the formula to calculate the influence coefficient at each historical moment. :

[0127] ;

[0128] In the formula, A constant greater than 1 This is the attenuation coefficient.

[0129] The influence coefficient is used to measure the degree of deviation between the protection unit setting value and the electrical quantity. The electrical quantity deviation is converted into a standardized influence index through an exponential decay function.

[0130] In practice, when the deviation decreases, the calculation results approach the theoretical extreme value, which intuitively represents the abnormality of the equipment's operating status.

[0131] S2061-2. Using the influence coefficients at the same historical moment as the dependent variable, and all local environmental parameters as independent variables, package them into a sample. Establish a linear regression model and set the intercept. and regression coefficients .

[0132] S2061-3, This Each sample is input into a linear regression model for training, with the independent variable in each sample serving as the input value. Output value The difference between the dependent variable and the differential variable is used as the difference coefficient. The expression is as follows:

[0133] ;

[0134] S2061-4. Adjust the intercept and regression coefficients until the sum of the difference coefficients of all samples is minimized, thus obtaining the trained protection unit. Relational expressions.

[0135] A mathematical mapping relationship between environmental parameters and influence coefficients is established. By fitting and training multiple sets of historical data, the linear influence weight of changes in each environmental parameter on the abnormal state of the protected unit is quantified, providing a basis for subsequent anomaly assessment.

[0136] S2062, Computational Protection Unit The sum of all regression coefficients in the relational expression Divide the regression coefficients corresponding to each environmental parameter by 1 / 2. Receive protection unit The second coefficient of each of the following environmental parameters .

[0137] S2063, respectively, power distribution equipment The fitting relationship expressions for each of the other protection units are determined, and the second coefficients of each environmental parameter under each protection unit are calculated.

[0138] S2064. Calculate the anomaly coefficient of each protection unit based on the first coefficient and the second coefficient. Anomaly coefficients of all protection units Summation as a power distribution device Abnormal index The formula for calculating the anomaly coefficient is as follows:

[0139] ;

[0140] In the formula, For the first The second coefficient of the environmental parameter, For the first The first coefficient of the environmental parameter, This is the sum of the first coefficients of all environmental parameters.

[0141] The overall abnormal risk level of the protection unit under severe conditions is quantified by combining the weight of the impact of a single environmental parameter on the protection unit (second coefficient) with the degree of abnormal fluctuation during the typhoon (first coefficient) through weighted ratio calculation.

[0142] S2065. Calculate the abnormality index of each power distribution device, and classify the power distribution devices with an abnormality index greater than the threshold as abnormal devices.

[0143] This system enables accurate identification and quantitative assessment of vulnerable power distribution equipment during typhoons. A typhoon evolution model is constructed through meteorological simulation, data fusion, and trajectory prediction. Combined with the electrical response characteristics of protection units and spatiotemporal coupling analysis, a dynamic anomaly index is generated, effectively screening high-risk power distribution equipment and avoiding resource waste on low-risk targets.

[0144] S300, predicting the time periods of typhoon entity passing through various anomalous devices, dividing overlapping time periods and setting time points. Analyzing the computing power allocation of each anomalous device at each time point, and ensuring the computing power allocation forms a smooth gradient over continuous time periods. Specifically, this includes:

[0145] S301. Analyze whether the time periods of each abnormal device overlap, and divide the duration of each abnormal device into fixed and non-unique periods as overlapping time periods. The abnormal devices corresponding to adjacent overlapping time periods are not completely the same.

[0146] In practice, adjacent overlapping time periods refer to two overlapping areas whose first and last digits are connected, not two adjacent overlapping time periods with a certain time interval.

[0147] S302, Setting Duration Divide the duration of each overlapping period by . The sample counts for each device are obtained. Within each overlapping time period, time points are evenly distributed according to the sample count, and the computing power allocation of all abnormal devices at each time point is analyzed. Specifically, this includes:

[0148] S3021, predicted typhoon body at the specified time point Substitute the various environmental parameters within the coverage area into the abnormal equipment. The expected influence coefficient of each protection unit is calculated from the relational expression of each protection unit.

[0149] S3022. Obtain the abnormality coefficient of each protection unit under the abnormal equipment, and calculate the abnormal equipment separately based on the expected impact coefficient. Allocation coefficient :

[0150] ;

[0151] In the formula, Abnormal equipment The total number of all protection units in the system. and The first The abnormality coefficient and expected impact coefficient of each protection unit.

[0152] S3023. Similarly, calculate the allocation coefficient for each abnormal device, and sum the allocation coefficients of all abnormal devices as the allocation index.

[0153] S3024. Divide the allocation coefficient of each abnormal device by the allocation index to obtain its respective computing power allocation ratio. Calculate the computing power allocation ratio of each abnormal device at each time point.

[0154] S303, Predicting Duration The duration of a single abnormal device within a timeframe that is not overlapping is considered an exclusive timeframe, while the duration of a timeframe that is neither overlapping nor exclusive is considered an idle timeframe.

[0155] In practice, overlapping periods represent times when multiple faulty devices coexist, and computing power is allocated according to their importance. Exclusive periods represent times when only a single faulty device is affected, and 100% computing power is allocated to them. Idle periods represent times when no faulty devices are affected, and no computing power is allocated to them.

[0156] S304. Set the computing power ratio to 0 during idle periods and set the computing power ratio to 100% for abnormal devices during exclusive periods.

[0157] S305. Perform a smoothing operation on the computing power allocation of all abnormal devices at each time point within the overlapping period, as well as the computing power allocation of abnormal devices corresponding to idle and exclusive periods.

[0158] S306. By constraining the jump variables in computing power allocation between adjacent time points through time series analysis, the computing power allocation values ​​of all abnormal devices in continuous time periods form a gradient approach process without sudden changes along the time axis.

[0159] A time-window-based elastic computing power allocation strategy is constructed. By modeling time-slicing (overlapping / exclusive / idle time periods) and allocation coefficients, computing resources can be scheduled on demand during the typhoon's evolution. Smooth gradient constraints are used to eliminate sudden changes in computing power, ensuring the continuous and stable execution of computing tasks.

[0160] S400 calculates the allocated computing power for each faulty device at different times based on the computing power allocation ratio, sets the refresh rate and resolution of the fault prediction engine based on the computing power allocation, and dynamically adjusts the setpoints for each protection unit. Specifically, this includes:

[0161] S401. Based on the time-varying supply capacity of the total computing resource pool and the computing power ratio of each abnormal device, the total computing power is allocated to each fault simulation task in a proportional relationship, and the available computing power quota for each abnormal device is generated. This quota represents the maximum amount of computing resources that can be consumed within the corresponding time window.

[0162] S402. Adjusting the computing power allocation affects the operation configuration of the fault simulation engine. Increasing the computing power allocation increases the number of simulation steps per unit time and refines the mesh generation accuracy (increasing refresh rate and spatial resolution). Decreasing the computing power allocation reduces the simulation iteration frequency and coarsens the model's order reduction scale (decreasing refresh rate and spatial resolution).

[0163] Under the constraint of limited computing power, the S403 fault prediction engine combines real-time collected environmental parameters (such as wind speed, pollution level, temperature and humidity) to generate protection setting adjustment schemes that adapt to the evolution of harsh environments through a time-series iterative optimization strategy, and sends them to the corresponding protection units in real time.

[0164] Highly adaptive protection setting optimization was achieved under limited computing power constraints. Simulation accuracy was flexibly adjusted through dynamic mapping between computing power quota and pre-simulation engine configuration.

[0165] In the specific implementation process, the optimal setpoint scheme is generated iteratively by combining real-time environmental parameters, which significantly improves the reliability of power distribution equipment protection under severe weather conditions.

[0166] Example 2: Please refer to Figure 2 The present invention also provides an automated power distribution equipment setting management system based on data analysis, including a dynamic sensing module, an anomaly analysis module, a computing power allocation module, and a setting management module.

[0167] The dynamic sensing module is used to collect GIS maps and environmental parameters within the coverage area, as well as the operating parameters of each power distribution device.

[0168] In the specific implementation process, GIS map information, global environmental parameters (such as wind speed, pollution level and temperature and humidity) and operating parameters of each power distribution equipment (including local environmental parameters and protection unit settings and electrical quantities) are collected in real time through sensor networks (such as Doppler weather radar) within the coverage area, while ensuring that the types and quantities of parameters are consistent.

[0169] It provides basic data support to achieve comprehensive and real-time perception of the environment and equipment status, laying the data foundation for subsequent typhoon forecasting and anomaly detection, reducing human intervention errors and improving data accuracy, thereby improving the system's response speed and initialization reliability.

[0170] The anomaly analysis module is used to set typhoon entities on GIS maps and predict their size and behavior, and to calculate anomaly indices and set abnormal equipment after screening power distribution equipment.

[0171] In the specific implementation process, typhoon entities are set on the GIS map, and the size and path of the typhoon are predicted by using the WRF meteorological model and Kalman filter data fusion technology. The abnormal index of the power distribution equipment is calculated by combining the Long Short-Term Memory (LSTM) spatiotemporal trajectory model and linear regression analysis (based on the first coefficient TFC and the second coefficient TSC), thereby screening out abnormal equipment (i.e. equipment whose abnormal index exceeds the threshold).

[0172] Accurately identify vulnerable power distribution equipment affected by typhoons, optimize resource allocation, reduce computational redundancy, and improve prediction accuracy by dynamically fitting relational expressions, thereby enhancing proactive early warning capabilities and decision-making efficiency under severe weather conditions.

[0173] The computing power allocation module is used to predict the time period during which the typhoon entity passes through various abnormal devices, divide overlapping time periods, and set time points. It analyzes the computing power allocation ratio of each abnormal device at each time point and makes the computing power allocation ratio form a smooth gradient over continuous time periods.

[0174] In the specific implementation process, the time period of the typhoon entity passing through each abnormal device is predicted, and overlapping time periods and exclusive time periods are divided (the number of samples is calculated by dividing the duration by the preset duration). The allocation coefficient is calculated at the time point (based on the protection unit abnormality coefficient and the expected impact coefficient of the abnormal device). Then, a smoothing operation is performed to make the computing power allocation in the continuous time period form a smooth gradient without abrupt changes.

[0175] Dynamically optimize the allocation of computing resources to avoid waste of computing resources, ensure that computing tasks flow efficiently in continuous time periods, improve system computing efficiency and reduce the risk of interruption, and provide stability assurance for setpoint management.

[0176] The setting management module calculates the computing power quota based on the computing power allocation ratio, thereby setting the refresh frequency and resolution of the fault prediction engine for abnormal equipment operation, and adjusting the setting value in real time for each protection unit.

[0177] In the specific implementation process, the computing power quota is calculated based on the computing power allocation ratio (the total computing resources are allocated proportionally), the operation configuration of the fault simulation engine is dynamically adjusted (such as refresh frequency and resolution, by changing the number of simulation steps and mesh subdivision accuracy), and the protection setting adjustment scheme is generated in combination with real-time environmental parameters, and then distributed to the protection unit in real time through a time-series iterative optimization strategy.

[0178] By achieving dynamic adaptive adjustment of protection settings under limited computing power constraints, the response accuracy and reliability under disasters such as typhoons can be improved, the risk of equipment failure can be reduced, and the resource utilization rate can be optimized, ultimately enhancing the overall safety and robustness of the power distribution system.

[0179] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, 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 process, method, article, or apparatus.

[0180] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A data analysis-based method for setting management of automated power distribution equipment, characterized in that: The method includes: S100: Collect GIS maps and global environmental parameters within the coverage area, as well as the operating parameters of each power distribution device; S200: Analyze environmental and operational parameters, set up typhoon entities on the GIS map and predict their size and behavior; after screening all power distribution equipment, calculate the anomaly index and set up abnormal equipment based on the anomaly index. S300: Predict the time period of the typhoon entity passing through each anomalous device, divide the overlapping time period and set time points; analyze the computing power ratio of each anomalous device at the time point, and make the computing power ratio form a smooth gradient in the continuous time period. S400 calculates the computing power allocated to each abnormal device at different times based on the computing power allocation ratio, sets the refresh frequency and resolution of the fault prediction engine during operation based on the computing power allocation, and dynamically adjusts the set value for each protection unit.

2. The method for setting management of automated power distribution equipment based on data analysis according to claim 1, characterized in that: In S100, the coverage area refers to the physical area jointly covered by the power distribution network and power distribution equipment; The continuous distribution of various environmental parameters in the airspace within the coverage area is monitored through sensor networks and Doppler weather radar technology. Global environmental parameters refer to the basic physical quantities that reflect the environmental state within the coverage area. Power distribution equipment refers to the equipment in a power system that converts medium voltage to low voltage and distributes electrical energy, including different protection units; a protection unit is an independent module in the power distribution equipment that has preset electrical quantity settings and operating logic. Each protection unit has set values ​​and electrical quantities. By comparing the difference between the real-time electrical quantities and the preset set values, the protection and isolation functions for overcurrent or short-circuit faults are executed. Operating parameters include local environmental parameters at the location of the power distribution equipment, as well as the settings and electrical quantities of each protection unit within it; the types and quantities of global environmental parameters and local environmental parameters are completely consistent.

3. The method for setting management of automated power distribution equipment based on data analysis according to claim 2, characterized in that: S200 includes: S201. Using the WRF meteorological model, the atmospheric state is simulated and analyzed based on global environmental parameters within the coverage area, and the core location and coverage of the typhoon entity are identified and marked on the GIS map. S202. Based on local environmental parameters at the location of power distribution equipment, Kalman filter data fusion technology is used to refine the core location and coverage boundary of the typhoon entity and improve spatial resolution. S203. Using a spatiotemporal trajectory prediction model based on a long short-term memory network, predict the duration of the typhoon based on refined typhoon parameters. The spatiotemporal evolution trajectory of the internal movement path; S204. Mark the location of each power distribution device on the GIS map, analyze the evolution of the coverage area as the typhoon moves according to its spatiotemporal evolution trajectory, and filter out all power distribution devices within the evolution area. S205. Predict the time period during which the typhoon will pass through each power distribution equipment, analyze the changes in environmental parameters within the typhoon's coverage area during the time period at each power distribution equipment, and calculate the first coefficient of each environmental parameter. ; S206, Count the number of all environmental parameters. Based on the operating parameters, fit the relationship expression of each protection unit in each power distribution device, calculate the abnormal index of the corresponding power distribution device in combination with the first coefficient, and set the abnormal device.

4. The method for setting management of automated power distribution equipment based on data analysis according to claim 3, characterized in that: S205 includes: S2051. Predicting the changes in the coverage area of ​​a typhoon as it moves according to its spatiotemporal evolution trajectory, and the distribution equipment... Time when the location was included in the coverage area and time out of coverage Combining time periods; S2052. Analyze the changes in environmental parameters within the typhoon's coverage area during the analysis period, and pre-set weighting coefficients for each environmental parameter. Substitute these values ​​into the formula to calculate the first coefficient of each environmental parameter: ； In the formula, These are the extreme values ​​of environmental parameters within a time period. This represents the average value of environmental parameters over a given time period. S2053, and so on, calculate the first coefficient of each environmental parameter based on the time period analysis of the location of each power distribution equipment.

5. The method for setting management of automated power distribution equipment based on data analysis according to claim 3, characterized in that: S206 includes: S2061, Obtaining power distribution equipment The operating parameters were analyzed, along with local environmental parameters and protection units at different historical moments. The set values ​​and electrical quantities are for the protection unit. The relational expression is obtained by fitting; S2062, Computational Protection Unit The sum of all regression coefficients in the relational expression Divide the regression coefficients corresponding to each environmental parameter by 1 / 2. Receive protection unit The second coefficient of each of the following environmental parameters ; S2063, respectively, power distribution equipment The fitting relationship expression for each of the other protection units is determined, and the second coefficient of each environmental parameter under each protection unit is calculated; S2064. Calculate the anomaly coefficient of each protection unit based on the first coefficient and the second coefficient. Anomaly coefficients of all protection units Summation as a power distribution device Abnormal index ; S2065. Calculate the abnormality index of each power distribution device, and classify the power distribution devices with an abnormality index greater than the threshold as abnormal devices.

6. The method for setting management of automated power distribution equipment based on data analysis according to claim 5, characterized in that: S2061 includes: S2061-1 Analysis of power distribution equipment The operating parameters are set evenly. Each historical moment; analysis of protection units at the same historical moment constant value and electrical quantities Substitute into the formula to calculate the influence coefficient at each historical moment. : ； In the formula, It is a constant greater than 1. The attenuation coefficient; S2061-2. Using the influence coefficients at the same historical moment as the dependent variable, and all local environmental parameters as independent variables and packaged into a sample; establish a linear regression model and set the intercept. and regression coefficients ; S2061-3, This Each sample is input into a linear regression model for training, with the independent variable in each sample serving as the input value. Output value The difference between the dependent variable and the differential variable is used as the difference coefficient; the expression is as follows: ； S2061-4. Adjust the intercept and regression coefficients until the sum of the difference coefficients of all samples is minimized, thus obtaining the trained protection unit. Relational expressions.

7. The method for setting management of automated power distribution equipment based on data analysis according to claim 5, characterized in that: In S2064, the formula for calculating the anomaly coefficient is as follows: ； In the formula, For the first The second coefficient of the environmental parameter, For the first The first coefficient of the environmental parameter, This is the sum of the first coefficients of all environmental parameters.

8. The method for setting management of automated power distribution equipment based on data analysis according to claim 3, characterized in that: The S300 includes: S301. Analyze whether the time periods of each abnormal device overlap, and divide the duration of each abnormal device into fixed and non-unique durations as overlapping time periods. The abnormal devices corresponding to adjacent overlapping time periods are not completely the same. S302, Set Duration Divide the duration of each overlapping period by 1 / 2. Each sample number is obtained; within each overlapping period, time points are evenly set according to the sample number, and the computing power allocation of all abnormal devices corresponding to each time point is analyzed. S303, Predicting Duration The duration of a single abnormal device within a period that is not overlapping is considered an exclusive period, while the duration of a period that is neither overlapping nor exclusive is considered an idle period. S304. Set the computing power allocation to 0 during idle periods and set the computing power allocation to 100% for abnormal devices during exclusive periods; S305. Perform a smoothing operation on the computing power allocation of all abnormal devices at each time point within the overlapping period, as well as the computing power allocation of the abnormal devices corresponding to the idle period and the exclusive period. S306. By constraining the jump variables in computing power allocation between adjacent time points through time series analysis, the computing power allocation values ​​of all abnormal devices in continuous time periods form a gradient approach process without sudden changes along the time axis.

9. The method for setting management of automated power distribution equipment based on data analysis according to claim 8, characterized in that: S302 includes: S3021, predicted typhoon body at the specified time point Substitute the various environmental parameters within the coverage area into the abnormal equipment. The expected influence coefficient of each protection unit is calculated from the relationship expression of each protection unit. S3022. Obtain the abnormality coefficient of each protection unit under the abnormal equipment, and calculate the abnormal equipment separately based on the expected impact coefficient. Allocation coefficient : ； In the formula, Abnormal equipment The total number of all protection units in the system. and The first The abnormal coefficient and expected impact coefficient of each protection unit; S3023. Similarly, calculate the allocation coefficient for each abnormal device, and sum the allocation coefficients of all abnormal devices as the allocation index. S3024. The allocation coefficient of the abnormal device is divided by the allocation index to obtain the computing power ratio of each device; the computing power ratio of each abnormal device at each time point is calculated.

10. A setpoint management system for automated power distribution equipment based on data analysis, characterized in that: The system includes a dynamic sensing module, an anomaly analysis module, a computing power allocation module, and a fixed value management module; The dynamic sensing module is used to collect GIS maps and environmental parameters within the coverage area, as well as the operating parameters of each power distribution device; The anomaly analysis module is used to set typhoon entities on GIS maps and predict their size and behavior, filter power distribution equipment, calculate anomaly indices, and set abnormal equipment. The computing power allocation module is used to predict the time period when the typhoon passes through each abnormal device, divide the overlapping time period and set the time point; analyze the computing power allocation ratio of each abnormal device at the time point, and make the computing power allocation ratio form a smooth gradient in the continuous time period. The setting management module calculates the computing power quota based on the computing power allocation ratio, thereby setting the refresh frequency and resolution of the fault prediction engine for abnormal equipment operation, and adjusting the setting value in real time for each protection unit.

Images