Power grid extreme rainstorm early warning method, device and equipment and storage medium

Abstract

This application discloses a method, device, equipment, and storage medium for early warning of extreme rainstorms in power grids, relating to the field of power meteorological disaster monitoring technology. The method for early warning of extreme rainstorms in power grids in this application involves acquiring the power grid topology, multi-source meteorological data of the power grid area, the first geographic coordinates of each device, and the grid coordinates of the meteorological data acquisition locations; using the coordinate system of the first geographic coordinates as the target coordinate system, determining the location coordinates corresponding to the grid coordinates; weighting and fusing the multi-source meteorological data of each location coordinate according to preset weights to obtain rainfall data; generating a rainfall grid field by combining the rainfall data and the power grid topology; determining the rainfall intensity of the grid where the device is located based on the rainfall grid field and the first geographic coordinates of the device; determining the risk level of each device by combining the distance between the device and the grid center point and the grid rainfall intensity; and finally generating early warning information for the corresponding device. This application can achieve accurate prediction and targeted early warning of extreme rainstorm risks in power grids, ensuring the safe operation of the power grid.

Description

Technical Field

[0001] This application relates to the field of power meteorological disaster monitoring technology, and in particular to methods, devices, equipment and storage media for early warning of extreme rainstorms in power grids. Background Technology

[0002] As the coverage of the power grid continues to expand, floods caused by extreme rainstorms have become a major natural factor leading to damage to power grid equipment and widespread power outages, placing higher demands on power grid rainstorm disaster monitoring technology.

[0003] To achieve heavy rainfall monitoring, some technologies rely on a single data source, such as weather station data, satellite remote sensing data, or weather forecast data, for independent analysis to obtain precipitation data. While this achieves basic heavy rainfall monitoring functions, it suffers from low accuracy and a lack of specificity. Therefore, how to achieve high-precision, scenario-adaptive monitoring of power grids for extreme heavy rainfall disasters has become an urgent problem to be solved. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and storage medium for early warning of extreme rainstorms in power grids, in order to at least solve the problems of low accuracy and lack of specificity in monitoring extreme rainstorm disasters in power grids in related technologies.

[0005] This application provides a method for early warning of extreme rainstorms in power grids, including: Acquire the power grid topology, meteorological data from different sources in the power grid area, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; among which, the devices include substations and transmission lines; Use the coordinate system where the first geographic coordinates are located as the target coordinate system, and determine the position coordinates of the grid points in the target coordinate system; Based on preset weights, the meteorological data from different sources corresponding to each location coordinate in the target coordinate system are weighted and fused to determine the rainfall data corresponding to the location coordinates; A rainfall grid field is generated based on the rainfall data and power grid topology corresponding to each location coordinate; Based on the rainfall grid field and the first geographic coordinates of each device, determine the rainfall intensity of the grid where each device is located; The risk level of each device is determined based on the distance between each device and the center point of its grid, and the rainfall intensity of the grid. Based on the risk level of each device, generate early warning information for each device.

[0006] This application also provides a power grid extreme rainstorm early warning device, including: The data acquisition module is used to acquire the power grid topology, meteorological data from different sources in the power grid area, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; among which, the devices include substations and transmission lines; The coordinate transformation module is used to take the coordinate system where the first geographic coordinates are located as the target coordinate system and determine the position coordinates of the grid points in the target coordinate system. The rainfall data determination module is used to perform weighted fusion of meteorological data from different sources corresponding to each location coordinate in the target coordinate system according to preset weights, and determine the rainfall data corresponding to the location coordinates. The grid field division module is used to generate a rainfall grid field based on the rainfall data and power grid topology corresponding to each location coordinate; The rainfall intensity determination module is used to determine the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device; The risk level determination module is used to determine the risk level of each device based on the distance between each device and the center point of its grid, and the rainfall intensity of the grid. The early warning information generation module is used to generate early warning information for each device based on its risk level.

[0007] This application also provides an electronic device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any of the above-described power grid extreme rainstorm early warning methods.

[0008] This application also provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of any of the above-described power grid extreme rainstorm early warning methods.

[0009] In some embodiments of this application, based on the power grid topology, meteorological data from different sources in the power grid area, and the coordinate information of the power grid equipment and the meteorological data collection locations, the grid coordinates of the meteorological data are first unified to the target coordinate system corresponding to the coordinates of the power grid equipment. Then, the multi-source meteorological data at each location in the target coordinate system are weighted and fused using preset weights to obtain rainfall data. After generating a rainfall grid field in conjunction with the power grid topology, the rainfall intensity of each grid where the equipment is located is matched. Finally, the risk level of the equipment is determined based on the distance between the equipment and the grid center point and the rainfall intensity, and early warning information is generated. In this way, the meteorological data and the power grid scenario can be accurately adapted through coordinate unification, and the reliability of rainfall data can be improved through weighted fusion of multi-source meteorological data. Risk levels can be differentiated for different locations and different rainfall conditions, and early warning information can be generated. Thus, the problems of low accuracy and lack of specificity in monitoring extreme rainstorm disasters in power grids in related technologies can be solved. Attached Figure Description

[0010] To more clearly illustrate the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a power grid extreme rainstorm early warning method provided for some embodiments of this application; Figure 2 This is the framework for the power grid extreme rainstorm early warning method of this application; Figure 3 This application provides a method and procedure for early warning of extreme rainstorms in power grids. Figure 4 Schematic diagram of a power grid extreme rainstorm early warning device provided for some embodiments of this application; Figure 5 A schematic diagram of the modules of an electronic device provided for some embodiments of this application. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the protection scope of this application.

[0013] It should be noted that, in the description of this application, 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 a process, method, article, or apparatus. The terms "first," "second," etc., in this application are used to distinguish similar objects and are not used to describe a specific order or sequence.

[0014] To enable those skilled in the art to better understand the present application, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In some technical solutions, power grid extreme rainstorm early warning methods often rely on a single meteorological data source, analyzing only ground meteorological station data, satellite remote sensing data, or weather forecast data to obtain precipitation data. Power grid rainstorm monitoring is then conducted based on this precipitation data, resulting in low monitoring accuracy and poor adaptability. Therefore, how to achieve high-precision power grid extreme rainstorm disaster monitoring that is adaptable to various scenarios has become an urgent problem to be solved.

[0016] Therefore, this application provides a method for early warning of extreme rainstorms in power grids, which can solve the above problems. This method can be applied to substations and transmission lines. (See also...) Figure 1 This is a flowchart illustrating a power grid extreme rainstorm early warning method provided in some embodiments of this application. Figure 1 In China, the method for issuing early warnings for extreme rainstorms on power grids includes the following steps: Step S101: Obtain the power grid topology, meteorological data from different sources in the area where the power grid is located, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; wherein, the devices include substations and transmission lines.

[0017] Specifically, the power grid topology originates from the power grid company and refers to the connection relationships and spatial distribution architecture of various equipment in the power grid, including but not limited to the coordinates and connection relationships of substations and transmission lines.

[0018] Specifically, meteorological data from different sources in the area where the power grid is located refers to multi-source meteorological data, which can represent parameters such as precipitation, temperature, humidity, and air pressure in the area where the power grid is located.

[0019] Specifically, the first geographic coordinates refer to the precise spatial coordinates of the power grid equipment, which serve as the core benchmark for subsequently determining the target coordinate system.

[0020] Specifically, the grid coordinates associated with the meteorological data collection locations refer to the spatial identifiers of the collection points of different meteorological data sources, which are the original coordinates of various types of meteorological data.

[0021] Understandably, it is necessary to first determine the coverage area of ​​the power grid monitoring, collect multi-source meteorological data of the corresponding area, obtain the first geographical coordinates of substations and transmission lines, and obtain the grid coordinates and original coordinate system information of each meteorological data.

[0022] Step S102: Take the coordinate system where the first geographic coordinates are located as the target coordinate system, and determine the position coordinates of the grid point coordinates in the target coordinate system.

[0023] Specifically, the target coordinate system refers to using the first geographic coordinates as the reference coordinates for subsequent coordinate transformations.

[0024] It is understandable that the coordinate system of the first geographic coordinate is the unified spatial reference coordinate system preset by the power grid equipment. By using the first geographic coordinate system as the target coordinate system, the coordinates of the collection grid points of meteorological data from different sources are transformed to the target coordinate system to achieve spatial registration of multi-source data.

[0025] Step S103: According to the preset weights, the meteorological data from different sources corresponding to each location coordinate in the target coordinate system are weighted and fused to determine the rainfall data corresponding to the location coordinates.

[0026] Specifically, the preset weight refers to the weight of meteorological data from different sources when weighted and fused. It is set based on the reliability of meteorological data, spatial coverage and terrain adaptability. The weights of meteorological data from different sources can be different, and the sum of the weights of all meteorological data at the same location coordinate is 1.

[0027] Specifically, rainfall data refers to the rainfall data obtained by weighted fusion of meteorological data from different sources, with each location coordinate corresponding to a unique rainfall data point at the same target time.

[0028] It is understandable that meteorological data from different sources in a certain area are weighted and fused according to preset weights to obtain the final rainfall data with location coordinates.

[0029] Step S104: Generate a rainfall grid field based on the rainfall data and power grid topology corresponding to each location coordinate.

[0030] Specifically, a rainfall grid field refers to transforming discrete location coordinate rainfall data into a continuous gridded rainfall distribution dataset. The grid size is set according to the density of power grid equipment, and each grid corresponds to a unique spatial coordinate and rainfall data.

[0031] Step S105: Determine the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device.

[0032] Understandably, a correlation between equipment and rainfall distribution is established based on the rainfall grid field and the first geographic coordinates of each device. For example, a power transmission line of a mountain power station spans 5 grids, and the rainfall intensities of the 5 grids are 18mm / h, 22mm / h, 20mm / h, 24mm / h and 21mm / h, respectively. The maximum value of 24mm / h is taken as the rainfall intensity of the transmission line.

[0033] Step S106: Determine the risk level of each device based on the distance between each device and the center point of the grid and the rainfall intensity of the grid.

[0034] Optionally, the risk level refers to a classification based on rainfall intensity, representing the safety status of equipment. Each piece of equipment has its corresponding risk level. Risk levels can be classified into the following four levels: 1) Level 1 (Blue): Rainfall intensity is 0-10 mm / h; 2) Level 2 (Yellow): Rainfall intensity is 10-20 mm / h; 3) Level 3 (Orange): Rainfall intensity is 20-30 mm / h; 4) Level 4 (Red): Rainfall intensity is 30-40 mm / h.

[0035] Optionally, the equipment exposure can be used as an auxiliary reference for risk level determination to quantify the degree of exposure impact of each grid in the rainfall grid field on the substation. Specifically, a Gaussian weight field is constructed based on the spatial distance between the grid and the equipment with the substation as the center, and the exposure weight of each grid on the substation is quantified by the Gaussian function. The specific algorithm is shown in expression (1).

[0036] (1) in, These are the Gaussian weight values ​​corresponding to the grid. This represents the straight-line distance from the grid center point to the substation. To influence the radius, different values ​​are taken based on the type of equipment. For example, 5km is taken for ultra-high voltage lines and 1km is taken for urban distribution networks.

[0037] Optionally, the risk level can be divided into the following four levels: 1) Level 1 (Blue): Rainfall intensity is 0-10 mm / h, and the exposure weight is 0-0.3; 2) Level 2 (Yellow): Rainfall intensity is 10-20 mm / h, and the exposure weight is 0.3-0.6; 3) Level 3 (Orange): Rainfall intensity is 20-30 mm / h, and the exposure weight is 0.6-0.9; 4) Level 4 (Red): Rainfall intensity is 30-40 mm / h, and exposure weight is >0.9.

[0038] Step S107: Generate early warning information for each device based on its risk level.

[0039] Specifically, early warning information refers to operation and maintenance prompts that are adapted to the risk level of power grid equipment, including but not limited to the longitude, latitude, time, rainfall intensity, and risk level of the equipment's location.

[0040] In summary, in the technical solutions of some embodiments of this application, based on the power grid topology, meteorological data from different sources in the power grid area, and the coordinate information of the power grid equipment and the meteorological data collection locations, the grid coordinates of the meteorological data are first unified to the target coordinate system corresponding to the coordinates of the power grid equipment. Then, the multi-source meteorological data at each location in the target coordinate system are weighted and fused using preset weights to obtain rainfall data. After generating a rainfall grid field in combination with the power grid topology, the rainfall intensity of each grid where the equipment is located is matched. Finally, the risk level of the equipment is determined based on the distance between the equipment and the grid center point and the rainfall intensity, and early warning information is generated. In this way, the meteorological data and the power grid scenario can be accurately adapted through coordinate unification, and the reliability of rainfall data can be improved through weighted fusion of multi-source meteorological data. Risk levels can be differentiated for different locations and different rainfall conditions, and early warning information can be generated. Thus, the problems of low accuracy and lack of specificity in monitoring extreme rainstorm disasters in power grids in related technologies can be solved.

[0041] In some embodiments, meteorological data from different sources include ground meteorological station data, satellite remote sensing data, and weather forecast data; Step S102, which uses the coordinate system containing the first geographic coordinates as the target coordinate system and determines the position coordinates of the grid points in the target coordinate system, includes: Step S1021: Obtain the second geographic coordinates associated with each meteorological station corresponding to the ground meteorological station data, the third geographic coordinates associated with each grid point corresponding to the satellite remote sensing data, and the fourth geographic coordinates associated with each grid point corresponding to the meteorological forecast data; wherein, the grid point coordinates include the second geographic coordinates, the third geographic coordinates, and the fourth geographic coordinates. Step S1022: Take the coordinate system where the first geographic coordinates are located as the target coordinate system, and convert the second, third, and fourth geographic coordinates into the corresponding position coordinates in the target coordinate system.

[0042] Optionally, ground meteorological station data refers to real-time data collected by on-site meteorological observation stations distributed within the power grid monitoring area, including but not limited to precipitation, temperature, humidity, and air pressure.

[0043] Optionally, satellite remote sensing data refers to regional precipitation data acquired by remote sensing detectors carried by meteorological satellites. Common data sources include IMERG (Integrated Multi-satellite Retrievals for GPM), CMORPH (CPC MORPHing technique), CINRAD (China New Generation Weather Radar), and MERRA-2 (Modern-Era Retrospective analysis for Research and Applications, Version 2). Remote sensing inversion algorithms convert satellite observation signals into precipitation data, including but not limited to satellite-based precipitation inversion data, meteorological radar-based precipitation inversion data, and atmospheric precipitable water inversion data based on satellite near-infrared bands.

[0044] Optionally, meteorological forecast data refers to future precipitation prediction data generated based on data weather forecasting models. The parameters include precipitation, temperature, humidity and air pressure, which can predict the occurrence of rainstorms in advance. The data source can be the ECMWF (European Centre for Medium-Range Weather Forecasts) numerical forecast.

[0045] Specifically, the second geographic coordinates refer to the spatial positioning coordinates of the ground meteorological station, which correspond to the actual installation location of each observation station and can directly reflect the spatial location of the station.

[0046] Specifically, the third geographic coordinate refers to the node coordinates of the satellite remote sensing data.

[0047] Specifically, the fourth geographic coordinate refers to the center coordinate of the meteorological forecast data grid, which represents the spatial location of each forecast unit.

[0048] Understandably, the process involves acquiring the attribute information of the second, third, and fourth geographic coordinates and their corresponding data sources, recording the original coordinate types and parameters of the three types of geographic coordinates, and then performing a spatial reference unification operation on the second, third, and fourth geographic coordinates to obtain the corresponding location coordinates in the first geographic coordinates, thereby achieving spatial registration of multi-source data.

[0049] In the above embodiments, by completing the acquisition and unified transformation of multi-source meteorological data coordinates and clarifying the attributes and transformation logic of various coordinates, the spatial reference deviation of different data sources can be effectively eliminated, ensuring that all meteorological grid coordinates and power grid equipment coordinates are in the same spatial dimension, thereby improving the accuracy of the power grid extreme rainstorm monitoring and early warning method.

[0050] In some embodiments, step S1022, which uses the coordinate system where the first geographic coordinates are located as the target coordinate system and converts the second, third, and fourth geographic coordinates into corresponding position coordinates in the target coordinate system, includes: Step a1: Determine the position coordinates based on the following formula:

[0051] in, This represents the original coordinates, which may include the second, third, or fourth geographic coordinates. Indicates the transformed position coordinates. Indicates the projection rotation angle. This represents the translation amount between the original coordinates and the position coordinates.

[0052] Specifically, the projection rotation angle is a fixed parameter calculated from the difference in projection azimuth angle between the original coordinate system and the target coordinate system, which can eliminate projection azimuth deviation.

[0053] Understandably, the coordinate transformation to the original coordinates is first achieved using a rotation matrix. Perform rotation correction to eliminate azimuth deviations between coordinate systems, and then superimpose translation amounts. The rotated coordinates are translated to the reference position of the target coordinate system, thus obtaining the precise position coordinates. .

[0054] In the above embodiments, coordinate transformation is performed by rotation matrix, which can standardize the coordinate transformation of multi-source meteorological data, ensure the adaptation of the second, third and fourth geographic coordinates to the target coordinate system, and provide data support for subsequent association of multi-source meteorological data by location coordinates.

[0055] In some embodiments, step S103, which involves weighted fusion of meteorological data from different sources corresponding to each location coordinate in the target coordinate system according to preset weights to determine the rainfall data corresponding to the location coordinates, includes: Step S1031: Synchronize the ground meteorological station data, satellite remote sensing data and meteorological forecast data along the time axis to obtain a complete time series dataset; Step S1032: Determine the weights of ground meteorological station data, satellite remote sensing data, and meteorological forecast data according to preset weights; Step S1033: Based on the weights of ground meteorological station data, satellite remote sensing data, and meteorological forecast data, the complete time series dataset for each location coordinate is weighted and fused to determine the rainfall data for each location coordinate.

[0056] Specifically, time axis synchronization refers to calibrating and aligning the time dimensions of three types of meteorological data based on a unified UTC (Coordinated Universal Time) time reference axis, and unifying and standardizing ground meteorological station data, satellite remote sensing data, and meteorological forecast data into time series data of the same duration.

[0057] Specifically, a complete time dataset refers to a collection of multi-source meteorological data that has been time-aligned. It is stored according to the coordinates of each location in the target coordinate system. Each location coordinate corresponds to a time-series record containing ground meteorological station data, satellite remote sensing data, and meteorological forecast data, which can ensure the matching of the three types of data at the same location and time.

[0058] Specifically, the preset weight refers to the differentiation coefficient formulated based on the inherent characteristics of multi-source meteorological data. The weight of ground meteorological station data is adjusted in combination with station density and terrain. The weight of satellite remote sensing data is set according to inversion accuracy and spatial integrity. The weight of meteorological forecast data is dynamically allocated with time. The sum of the three types of weights at the same location coordinate is 1.

[0059] Understandably, the process involves first aligning the multi-source data in the time domain through time axis synchronization, then fusing the multi-source data through differentiated weight allocation, and finally determining the rainfall data corresponding to each location coordinate.

[0060] In the above embodiments, the problem of data temporal domain adaptation is solved first, then the weights are reasonably allocated, and finally accurate rainfall data is obtained through quantization calculation. This can achieve adaptation of multi-source data and improve the scenario adaptability of the early warning method.

[0061] In some embodiments, step S1031 involves synchronizing the ground weather station data, satellite remote sensing data, and weather forecast data along the time axis to obtain a complete time series dataset, including: Step b1: Arrange the ground weather station data, satellite remote sensing data and weather forecast data in time sequence to obtain the corresponding ground weather station data sequence, satellite remote sensing data sequence and weather forecast data sequence; Step b2 involves synchronizing the timelines of ground meteorological station data sequences, satellite remote sensing data sequences, and meteorological forecast data sequences to determine the complete time series dataset.

[0062] Specifically, the ground weather station data sequence refers to the time series collection of ground weather station data sources formed by arranging them in time sequence. It is stored according to the location coordinates of the ground weather stations, and each record corresponds to rainfall data with a unique timestamp.

[0063] Specifically, satellite remote sensing data sequences and weather forecast data sequences are similar to ground weather station data sequences.

[0064] Understandably, before timeline synchronization, data time-series alignment is performed first, resulting in a complete time-series dataset for each location coordinate, corresponding to ground meteorological station data, satellite remote sensing data, and weather forecast data.

[0065] In the above embodiments, by splitting the time sequence arrangement and synchronizing the time axis, the time domain of multi-source meteorological data is aligned, which solves the problem of inconsistent time sequence of the original data and provides a data foundation for subsequent weighted fusion of data.

[0066] In some embodiments, step b2, which involves synchronizing the ground weather station data sequence, satellite remote sensing data sequence, and weather forecast data sequence along the time axis to determine the complete time series dataset, includes: Step c1, based on the following formula, determine the complete time series dataset:

[0067] in, Indicates the first Target time within each interpolation interval The data values ​​are synchronized along the timeline and include sequence values ​​from ground meteorological station data sequences, satellite remote sensing data sequences, and meteorological forecast data sequences. This indicates the target time set after the timeline is synchronized. This represents a time point in the original meteorological data sequence. , , and Indicates the first The coefficients determined within the interpolation intervals, the original meteorological data sequence includes the data sequence of ground meteorological stations, the data sequence of satellite remote sensing and the data sequence of meteorological forecasts.

[0068] Specifically, a cubic polynomial interpolation formula is used to fill the data gaps in the time axis synchronization of multi-source meteorological data sequences, ultimately achieving synchronization of the three types of data sequences at all target times. Temporal alignment.

[0069] In the above embodiments, the time axis synchronization of multi-source meteorological data is achieved by using a cubic polynomial interpolation formula, which can solve the time domain adaptation of different data sources, and the accuracy of the synchronized data is ensured by smooth fitting, providing a data foundation for subsequent weighted fusion of data.

[0070] In some embodiments, step S105, determining the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device, includes: Step S1051: Determine the rainfall intensity of each grid cell containing each device based on the following formula:

[0071] in, Indicates the first The rainfall intensity of the grid cell where each device is located. Indicates the first The weighting coefficient of rainfall intensity at each location coordinate for the rainfall intensity of the grid point where the device is located. Indicates the first Rainfall data at each location coordinate.

[0072] Optionally, before calculating rainfall data, data preprocessing operations are performed to detect and remove outliers from ground meteorological station data, satellite remote sensing data, and weather forecast data based on the Grubbs criterion.

[0073] Optionally, the accuracy of rainfall intensity data can be optimized by combining atmospheric water vapor distribution characteristics to compensate for the deviation caused by water vapor interference during the satellite remote sensing precipitation inversion process. Specifically, the rainfall intensity can be corrected using satellite atmospheric precipitable water vapor (PWV) data. The specific algorithm is shown in expression (2).

[0074] (2) in, The calibrated PWV value. This is the original PWV value. For regional calibration coefficients, This represents the regional average water vapor concentration. The standard deviation of water vapor in the region.

[0075] Optionally, trend constraints and accuracy optimization of meteorological forecast data can be achieved through time series modeling. Specifically, the AutoRegressive Integrated Moving Average Model (ARIMA) (2,1,1) is used to stabilize the original time series of numerical forecasts, transforming the non-stationary rainfall forecast series into a stationary time series, thereby completing the time series constraints. The specific algorithm is shown in expression (3).

[0076] (3) in, For lag operators, and These are the autoregressive coefficients of the model. The moving average coefficient is... The first difference of the rainfall forecast sequence, It is a white noise sequence.

[0077] Specifically, The weighting coefficients for location coordinates and rainfall data. It can be calculated from expression (4).

[0078] (4) in, For elevation gradient, This is the terrain correction factor.

[0079] Specifically, the elevation gradient characterizes the steepness of the terrain in the area where the location coordinates are located. The larger its absolute value, the steeper the terrain, indicating that the rainfall data at that location is more affected by terrain. The terrain correction factor is used to adjust the elevation gradient. The degree of impact needs to be dynamically set in conjunction with the terrain type of the area where the power grid is located.

[0080] Understandably, by using a weighted summation formula, weights are assigned based on the mountainous terrain, and the rainfall data of the grid where the device is located is integrated. The rainfall data after weighted summation can better reflect the actual situation of each location coordinate.

[0081] In the above embodiments, terrain factors are incorporated into the weight coefficient setting system, so that the weight allocation is adapted to the terrain characteristics, thereby improving the accuracy of rainfall intensity calculation for the grid where the equipment is located in different terrain areas.

[0082] To facilitate understanding, an example will be used as an illustration below.

[0083] Specifically, the example area has complex terrain and significant elevation differences, making it a high-risk area for rainstorm disasters. The specific steps are as follows: 1) Multi-source data collaborative acquisition. Multi-source data were acquired based on the ultra-high voltage transmission corridor, including: real-time data from 83 ground meteorological stations with a time resolution of 10 minutes; atmospheric precipitable water products from Fengyun-4A satellite with a spatial resolution of 0.1° and a time resolution of 30 minutes; ECMWF numerical weather prediction data with a spatial resolution of 0.1° and a time resolution of 1 hour; and power grid GIS (Geographic Information System) data, including coordinate information of ±800kV transmission lines and converter stations, as well as a 20-kilometer buffer zone.

[0084] 2) Spatiotemporal benchmark unification. Quality control was performed on multi-source data, and outliers were removed based on the Grubbs criterion, eliminating data from 12 stations, accounting for 14.5%. Data weights were set as follows: satellite data weight 0.6, ground station data weight 0.8, and numerical weather prediction weight 0.7. Spatiotemporal registration of the multi-source data was performed using a geographic information system, unifying them to the WGS-84 coordinate system and UTC time benchmark.

[0085] 3) Gridded modeling. A basic gridded field is generated using the terrain-constrained kriging interpolation method, with terrain correction factors... A value of 0.25 was used. Correction was performed using water vapor data from the Fengyun-4 satellite; the regional calibration coefficient was [value missing]. Take 0.35, the regional average water vapor value The value is 42.3, with a standard deviation of 42.3. The value is 8.7. The correction formula is shown in expression (5).

[0086] (5) ARIMA(2,1,1) model was used for time series forecasting with a forecast step size of 6 hours. A Gaussian weighted field was constructed centered on the substation, with an influence radius of... Take a 5km radius and calculate the equipment exposure weight.

[0087] 4) Dynamic Risk Mapping. Based on the rainstorm intensity grid field and equipment exposure weights, a four-level risk warning product is generated. The output is a risk raster map in GeoTIFF (GeoTIFF Format) format, with a spatial resolution of 0.1° and a temporal resolution of 15 minutes.

[0088] See also Figure 2 , Figure 2 This is the framework of the power grid extreme rainstorm early warning method of this application. Figure 2In this architecture, the data source layer serves as the data input, collecting heterogeneous data from multiple sources, including ground meteorological station data, satellite remote sensing data, numerical weather prediction data, and power grid topology data. The fusion processing layer is the core of the data processing, handling and fusing the input data, including time base unification, time axis synchronization, and quality control. The application layer is the output, enabling visualization and decision-making regarding rainstorm risks.

[0089] See also 3. Figure 3 This application presents a method and procedure for early warning of extreme rainstorms in power grids. Figure 3 The process involves first acquiring multi-source data collaboratively, then unifying the time base, followed by gridded modeling and dynamic risk mapping, and finally outputting the results.

[0090] Corresponding to the power grid extreme rainstorm early warning method, this application also provides a power grid extreme rainstorm early warning device. (See also...) Figure 4 This is a schematic diagram of a power grid extreme rainstorm early warning device provided in some embodiments of this application. Figure 4 In China, the power grid extreme rainstorm early warning device includes: The data acquisition module 401 is used to acquire the power grid topology, meteorological data from different sources in the area where the power grid is located, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; wherein, the devices include substations and transmission lines; The coordinate transformation module 402 is used to take the coordinate system where the first geographic coordinates are located as the target coordinate system and determine the position coordinates of the grid point in the target coordinate system. The rainfall data determination module 403 is used to perform weighted fusion of meteorological data from different sources corresponding to each location coordinate in the target coordinate system according to preset weights, and determine the rainfall data corresponding to the location coordinates. The grid field division module 404 is used to generate a rainfall grid field based on the rainfall data and power grid topology corresponding to each location coordinate; The rainfall intensity determination module 405 is used to determine the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device; The risk level determination module 406 is used to determine the risk level of each device based on the distance between each device and the center point of the grid and the rainfall intensity of the grid. The early warning information generation module 407 is used to generate early warning information for each device based on the risk level of each device.

[0091] In some embodiments, meteorological data from different sources include ground meteorological station data, satellite remote sensing data, and weather forecast data; the coordinate transformation module 402 includes: The coordinate acquisition unit is used to acquire the second geographic coordinates associated with each meteorological station corresponding to the ground meteorological station data, the third geographic coordinates associated with each grid point corresponding to the satellite remote sensing data, and the fourth geographic coordinates associated with each grid point corresponding to the meteorological forecast data; wherein, the grid point coordinates include the second geographic coordinates, the third geographic coordinates, and the fourth geographic coordinates. The coordinate transformation unit is used to convert the second, third, and fourth geographic coordinates into their corresponding position coordinates in the target coordinate system, using the coordinate system where the first geographic coordinates are located.

[0092] In some embodiments, the coordinate transformation unit includes: The coordinate transformation sub-unit is used to determine the position coordinates based on the following formula:

[0093] in, This represents the original coordinates, which may include the second, third, or fourth geographic coordinates. Indicates the transformed position coordinates. Indicates the projection rotation angle. This represents the translation amount between the original coordinates and the position coordinates.

[0094] In some embodiments, the rainfall data determination module 403 includes: The time axis synchronization unit is used to synchronize ground meteorological station data, satellite remote sensing data and weather forecast data on the time axis to obtain a complete time series dataset. The weight determination unit is used to determine the weights of ground meteorological station data, satellite remote sensing data, and meteorological forecast data according to preset weights. The rainfall data determination unit is used to perform weighted fusion of the complete time series dataset for each location coordinate based on the weights of ground meteorological station data, satellite remote sensing data, and meteorological forecast data, in order to determine the rainfall data for each location coordinate.

[0095] In some embodiments, the time axis synchronization unit includes: The sequence generation subunit is used to arrange ground meteorological station data, satellite remote sensing data and weather forecast data in time sequence to obtain the corresponding ground meteorological station data sequence, satellite remote sensing data sequence and weather forecast data sequence; The timeline synchronization subunit is used to synchronize the timelines of ground meteorological station data sequences, satellite remote sensing data sequences, and meteorological forecast data sequences to determine the complete time series dataset.

[0096] In some embodiments, the time axis synchronization subunit includes: Interpolation subunits are used to determine the complete time series dataset based on the following formula:

[0097] in, Indicates the first Target time within each interpolation interval The data values ​​are synchronized along the timeline and include sequence values ​​from ground meteorological station data sequences, satellite remote sensing data sequences, and meteorological forecast data sequences. This indicates the target time set after the timeline is synchronized. This represents a time point in the original meteorological data sequence. , , and Indicates the first The coefficients determined within the interpolation intervals, the original meteorological data sequence includes the data sequence of ground meteorological stations, the data sequence of satellite remote sensing and the data sequence of meteorological forecasts.

[0098] In some embodiments, the rainfall intensity determination module 405 includes: The rainfall intensity determination unit is used to determine the rainfall intensity of each grid cell containing the device based on the following formula:

[0099] in, Indicates the first The rainfall intensity of the grid cell where each device is located. Indicates the first The weighting coefficient of rainfall intensity at each location coordinate for the rainfall intensity of the grid point where the device is located. Indicates the first Rainfall data at each location coordinate.

[0100] For a description of the features in the embodiment corresponding to the power grid extreme rainstorm early warning device, please refer to the relevant description of the embodiment corresponding to the sample data processing method, which will not be repeated here.

[0101] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method.

[0102] See also Figure 5 The embodiments of this application also provide an electronic device, including a memory 10 and a processor 20, wherein the memory 10 stores a computer program and the processor 20 is configured to run the computer program to perform the steps in any of the above embodiments of the power grid extreme rainstorm early warning method.

[0103] Embodiments of this application also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to execute the steps in any of the above embodiments of the power grid extreme rainstorm early warning method when it is run.

[0104] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0105] The embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements the steps in any of the above embodiments of the power grid extreme rainstorm early warning method.

[0106] Embodiments of this application also provide another computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps in any of the above embodiments of the power grid extreme rainstorm early warning method.

[0107] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0108] The above provides a detailed description of a power grid extreme rainstorm early warning method, apparatus, device, and storage medium provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only intended to help understand the method and core ideas of this application. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from its principles, and these improvements and modifications also fall within the protection scope of the claims of this application.

Claims

1. A method for early warning of extreme rainstorms in power grids, characterized in that, The method includes: The system acquires the power grid topology, meteorological data from different sources in the area where the power grid is located, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; wherein, the devices include substations and transmission lines; Using the coordinate system where the first geographic coordinates are located as the target coordinate system, determine the position coordinates of the grid point coordinates in the target coordinate system; According to preset weights, the meteorological data from different sources corresponding to each location coordinate in the target coordinate system are weighted and fused to determine the rainfall data corresponding to the location coordinate; A rainfall grid field is generated based on the rainfall data and power grid topology corresponding to each of the aforementioned location coordinates; Based on the rainfall grid field and the first geographic coordinates of each device, the rainfall intensity of each grid cell containing the device is determined; The risk level of each device is determined based on the distance between each device and the center point of the grid, and the rainfall intensity of the grid. Based on the risk level of each device, a warning message is generated for each device.

2. The power grid extreme rainstorm early warning method according to claim 1, characterized in that, The meteorological data from different sources include ground meteorological station data, satellite remote sensing data, and weather forecast data; The step of using the coordinate system where the first geographic coordinates are located as the target coordinate system and determining the position coordinates of the grid point coordinates in the target coordinate system includes: The system acquires the second geographic coordinates associated with each meteorological station corresponding to the ground meteorological station data, the third geographic coordinates associated with each grid point corresponding to the satellite remote sensing data, and the fourth geographic coordinates associated with each grid point corresponding to the weather forecast data; wherein the grid point coordinates include the second geographic coordinates, the third geographic coordinates, and the fourth geographic coordinates. Using the coordinate system where the first geographic coordinates are located as the target coordinate system, the second, third, and fourth geographic coordinates are converted into corresponding position coordinates in the target coordinate system.

3. The power grid extreme rainstorm early warning method according to claim 2, characterized in that, The step of using the coordinate system where the first geographic coordinates are located as the target coordinate system and converting the second, third, and fourth geographic coordinates into corresponding position coordinates in the target coordinate system includes: The position coordinates are determined based on the following formula: in, This represents the original coordinates, which include the second, third, or fourth geographic coordinates. Indicates the transformed position coordinates. Indicates the projection rotation angle. This represents the translation amount of the original coordinates and the position coordinates.

4. The power grid extreme rainstorm early warning method according to claim 2, characterized in that, The step of weightedly fusing meteorological data from different sources corresponding to each location coordinate in the target coordinate system according to preset weights to determine the rainfall data corresponding to the location coordinate includes: The ground meteorological station data, satellite remote sensing data, and meteorological forecast data are synchronized along the time axis to obtain a complete time series dataset. The weights of ground meteorological station data, satellite remote sensing data, and meteorological forecast data are determined according to preset weights. Based on the weights of the ground meteorological station data, satellite remote sensing data, and meteorological forecast data, the complete time series datasets for each location coordinate are weighted and fused to determine the rainfall data for each location coordinate.

5. The power grid extreme rainstorm early warning method according to claim 4, characterized in that, The process of synchronizing the ground meteorological station data, satellite remote sensing data, and meteorological forecast data along the time axis yields a complete time-series dataset, including: The ground meteorological station data, satellite remote sensing data, and weather forecast data are arranged in time sequence to obtain the corresponding ground meteorological station data sequence, satellite remote sensing data sequence, and weather forecast data sequence; The ground meteorological station data sequence, satellite remote sensing data sequence, and meteorological forecast data sequence are synchronized along the time axis to determine a complete time series dataset.

6. The power grid extreme rainstorm early warning method according to claim 5, characterized in that, The process of synchronizing the ground meteorological station data sequence, satellite remote sensing data sequence, and meteorological forecast data sequence along the time axis to determine the complete time series dataset includes: The complete time series dataset is determined based on the following formula: in, Indicates the first Target time within each interpolation interval The data values ​​are synchronized along the timeline, including sequence values ​​from the ground meteorological station data sequence, satellite remote sensing data sequence, and meteorological forecast data sequence. This indicates the target time set after the timeline is synchronized. This represents a time point in the original meteorological data sequence. , , and Indicates the first The coefficients determined within an interpolation interval, wherein the original meteorological data sequence includes the above-mentioned ground meteorological station data sequence, satellite remote sensing data sequence, and meteorological forecast data sequence.

7. The power grid extreme rainstorm early warning method according to claim 1, characterized in that, The step of determining the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device includes: The rainfall intensity of each grid cell containing the device is determined based on the following formula: in, Indicates the first The rainfall intensity of the grid cell where the device is located. Indicates the first The weighting coefficient of rainfall intensity at each location coordinate to the grid point where the device is located. Indicates the first Rainfall data at each location coordinate.

8. A power grid extreme rainstorm early warning device, characterized in that, The device includes: The data acquisition module is used to acquire the power grid topology, meteorological data from different sources in the area where the power grid is located, the first geographic coordinates associated with each device in the power grid, and the grid coordinates associated with the meteorological data collection location; wherein, the device includes substations and transmission lines; The coordinate transformation module is used to take the coordinate system where the first geographic coordinates are located as the target coordinate system and determine the position coordinates of the grid point coordinates in the target coordinate system. The rainfall data determination module is used to perform weighted fusion of meteorological data from different sources corresponding to each location coordinate in the target coordinate system according to preset weights, so as to determine the rainfall data corresponding to the location coordinate; The grid field division module is used to generate a rainfall grid field based on the rainfall data and power grid topology corresponding to each of the location coordinates; The rainfall intensity determination module is used to determine the rainfall intensity of each grid cell containing each device based on the rainfall grid field and the first geographic coordinates of each device; The risk level determination module is used to determine the risk level of each device based on the distance between each device and the center point of the grid and the rainfall intensity of the grid. The early warning information generation module is used to generate early warning information for each of the devices based on the risk level of each device.

9. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the power grid extreme rainstorm early warning method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of the power grid extreme rainstorm early warning method as described in any one of claims 1 to 7.

Images