Power distribution network pre-disaster power failure risk assessment method under typhoon-rainstorm-flood disaster chain

Abstract

The invention discloses a power distribution network pre-disaster power failure risk assessment method under a typhoon-rainstorm-flood disaster chain. The method comprises the following steps: predicting a typhoon rainfall time sequence of a target area from a data driving angle based on a hybrid deep learning model; a 1D-2D coupling rainstorm flood model of the target area is constructed, the typhoon rainfall time sequence is used as input, the urban inland inundation ponding condition under typhoon attack is simulated from the perspective of physical driving, and the flood ponding depth after typhoon landing is obtained; the power failure risk of the power distribution and transformation equipment is evaluated from environmental and social perspectives by utilizing a geographic detector, driving force of each environmental factor and each social factor to a power failure event is determined, and the power failure risk of the power distribution and transformation equipment under a typhoon-rainstorm-flood disaster chain is calculated by taking the driving force of each factor as a weight and utilizing weighted average; wherein the environmental factors comprise the flood ponding depth. The method can effectively predict typhoon rainfall and flood water depth, comprehensively assesses the power failure risk of the power distribution network, and facilitates the formulation of a flood control strategy of the power distribution network.

Description

Technical Field

[0001] The present invention belongs to the technical field of distribution networks, and in particular relates to a method for assessing the risk of power outages before a typhoon-rainstorm-flood disaster chain occurs in a distribution network. Background Art

[0002] For a long time, power grids in coastal areas have suffered from typhoon disasters, and a lot of resources are consumed every year for disaster prevention and mitigation. In addition to the direct impact of strong winds on the power grid, typhoons are also very likely to trigger a chain of rainstorms and floods, causing power distribution and transformation equipment to be flooded and power outages. Typhoon "Fireworks" in 2021, Typhoon "Siam" in 2022, and Typhoon "Tali" in 2023 all brought heavy rainfall, causing large-scale urban waterlogging and accumulation of water, seriously threatening the safe and stable operation of the power grid. Therefore, it is necessary to systematically study the disaster-causing mechanism of the typhoon-rainstorm-flood disaster chain, quantify the disaster prevention capabilities of the distribution network, and identify areas with high risk of power outages.

[0003] However, in the existing distribution network power outage risk assessment technology, the hydrological and hydrodynamic model can simulate the distribution of pipelines and micro-topography in the disaster-stricken area and dynamically analyze the evolution of floods, but it lacks typhoon scenario applications and does not divide the risk level for the distribution network. In addition, most current studies only assess the power outage risk from the perspective of numerical statistics, without considering the spatial characteristics between the flood water accumulation points and various influencing factors, and cannot provide more effective suggestions for disaster prevention and mitigation. To this end, it is necessary to analyze the impact of the typhoon-rainstorm-flood disaster chain on the urban distribution network, propose a quantitative assessment model for the power outage risk of the distribution network under the typhoon-rainstorm-flood disaster chain, and improve the distribution network's ability to prevent the typhoon-rainstorm-flood disaster chain. Summary of the invention

[0004] The purpose of the present invention is to provide a method for assessing the risk of power outages before a typhoon-rainstorm-flood disaster chain. By analyzing the risk of power outages before a typhoon-rainstorm-flood disaster chain, the ability of the distribution network to prevent the typhoon-rainstorm-flood disaster chain can be improved.

[0005] In a first aspect of the present invention, a method for assessing the risk of power outage before a typhoon-rainstorm-flood disaster in a distribution network is provided. The method comprises:

[0006] Predict typhoon rainfall time series in target areas from a data-driven perspective based on a hybrid deep learning model;

[0007] Construct a 1D-2D coupled rainstorm flood model for the target area, take the typhoon rainfall time series as input, simulate the urban waterlogging under the typhoon from the perspective of physical drive, and obtain the flood depth after the typhoon lands.

[0008] Using a geographical detector, evaluate the power distribution and transformation equipment outage risk from environmental and social perspectives, and determine the driving forces of various environmental and social factors on outage events. Taking the driving forces of each factor as weights, calculate the power distribution and transformation equipment outage risk under the typhoon-rainstorm-flood disaster chain using weighted average; among them, the environmental factors include the depth of floodwater accumulation.

[0009] In some embodiments, predict the typhoon rainfall time series of the target area from a data-driven perspective based on a hybrid deep learning model, including:

[0010] Obtain the meteorological data and geographical data of the target area, and perform data preprocessing;

[0011] Input the preprocessed meteorological data and geographical data into the hybrid deep learning model to predict the typhoon rainfall time series of the target area.

[0012] In some embodiments, the meteorological data includes average wind speed, wind direction, gust, average temperature, and relative humidity, the geographical data includes geographical elevation, slope, aspect, land cover type, longitude, and latitude, the data preprocessing is data normalization, and the hybrid deep learning model is a CNN-LSTM-XGBoost model based on an attention mechanism.

[0013] In some embodiments, construct a 1D-2D coupled rainstorm and flood model for the target area, use the typhoon rainfall time series as the input, and simulate the urban waterlogging and water accumulation situation under typhoon invasion from a physically driven perspective to obtain the depth of floodwater accumulation after the typhoon makes landfall, including:

[0014] Construct a one-dimensional road confluence model, that is, establish a one-dimensional drainage pipe network using the stormwater management model SWMM, and input surface roughness, land cover type, characteristic width, Manning's N value, surface depression storage parameters, and typhoon rainfall time series to calculate the pipe network confluence;

[0015] Use the InfoWorks ICM-2D module to establish a two-dimensional surface water dynamics model, and input surface roughness, land cover type, characteristic width, Manning's N value, surface depression storage parameters, traffic road network, and typhoon rainfall time series to simulate the surface flood flow direction and water accumulation process;

[0016] Through the dynamic coupling interface of InfoWorks ICM, realize the real-time data interaction between the one-dimensional road confluence model and the two-dimensional surface water dynamics model, so as to integrate the pipe network confluence with the surface flood flow direction and water accumulation process, construct a one-dimensional-two-dimensional coupled typhoon rainstorm and flood prediction model, and simulate the urban flood and water accumulation situation under typhoon invasion from a physically driven perspective to obtain the depth of floodwater accumulation after the typhoon makes landfall.

[0017] In some of these embodiments, the one-dimensional to two-dimensional ponding water flow exchange formula is as follows:

[0018]

[0019] In the formula, Q n is the exchange flow between the one-dimensional road confluence model and the two-dimensional surface water dynamics model; c0 is the overflow coefficient of the drain pipe outlet; c w is the weir flow coefficient; w is the perimeter of the drain manhole; A 1D-2D is the cross-sectional area for the flow exchange between the pipe network and the surface, i.e., the area of the drain manhole; g is the gravity coefficient; h 1D , h 2D , H respectively represent the water level at the node of the one-dimensional drainage pipe network, the two-dimensional surface water level, and the surface elevation.

[0020] In some of these embodiments, constructing a one-dimensional road confluence model specifically includes:

[0021] Based on all the power transformation and distribution equipment in the target area, using Thiessen polygons to divide the target area into several sub-catchments, and using ArcGIS software to associate the surface roughness, surface cover type, and Manning's N value with each sub-catchment;

[0022] Based on different underlying surface types, divide the sub-catchments into permeable areas and impermeable areas, and calculate the Manning's N value of each sub-catchment by weighted average according to the area of different underlying surface types in the sub-catchments;

[0023] Calculate the surface depression storage parameter of each sub-catchment;

[0024] Calculate the characteristic width of the sub-catchment. The specific expression is as follows:

[0025]

[0026] In the formula, D width is the characteristic width of the sub-catchment; K is the model calibration parameter; is the area of the k-th sub-catchment;

[0027] Input the surface roughness, surface cover type, characteristic width, Manning's N value, surface depression storage parameter, and typhoon rainfall time series into the one-dimensional drainage pipe network SWMM model to calculate the pipe network confluence in the target area.

[0028] In some of these embodiments, the surface cover type of the sub-catchment is divided into permeable areas and impermeable areas. The permeable areas include forest land, grassland, water area, cultivated land, and natural bare land, and the impermeable areas include housing buildings, roads, and artificial bare land;

[0029] The underlying surface types of sub-catchments are divided into permeable surfaces, impermeable surfaces and others. Permeable surfaces include cultivated land, forest land, grassland and natural bare land. Impermeable surfaces include artificial surfaces. Others include water areas and wetlands.

[0030] In some of these embodiments, a geographical detector is used to evaluate the power outage risk of power transformation and distribution equipment from environmental and social perspectives, and to determine the driving forces of various environmental factors and social factors on power outage events. Using the driving forces of each factor as weights, the power outage risk of power transformation and distribution equipment under the typhoon-rainstorm-flood disaster chain is calculated by weighted average, including:

[0031] Use the geographical data processing tools in ArcGIS Pro to extract the environmental factors and social factors at the locations of each power transformation and distribution equipment; among them, environmental factors include floodwater depth, rainfall, average temperature, wind speed, relative humidity, gust, geographical elevation and land use type; social factors include population and GDP;

[0032] Regarding each factor as an independent variable and the power outage time of power transformation and distribution equipment as a dependent variable, use the factor detection module in the geographical detector to determine the driving force of each factor. The expression is as shown in the following formula:

[0033]

[0034]

[0035] In the formula, W k ∈[0,1] is the driving force of each factor, and the larger its value, the stronger the explanatory power of the factor; h = 1,..., L is the partition of the target area; k is the kth factor; N h and N are the number of units in area h and the total number of units in the target area respectively; and σ 2 are the variance of the dependent variable in area h and the variance of the dependent variable in the whole area respectively; V SSW and V SST are the sum of partition variances and the sum of variances in the whole area respectively;

[0036] Using the driving forces of each factor as weights, the power outage risk of power transformation and distribution equipment under the typhoon-rainstorm-flood disaster chain is calculated by weighted average.

[0037] According to the second aspect of the present invention, an electronic device is provided, including: a processor and a memory. The memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the power grid pre-disaster power outage risk assessment method under the typhoon-rainstorm-flood disaster chain described in any item of the first aspect are implemented.

[0038] According to a third aspect of the present invention, there is provided a readable storage medium storing a program or instructions, which when executed by a processor, implement the steps of the method for pre-disaster power outage risk assessment of a distribution network under a typhoon-rainstorm-flood disaster chain described in any one of the first aspects.

[0039] Generally speaking, compared with the prior art through the above technical solutions conceived by the present invention, the following beneficial effects can be achieved:

[0040] The present invention proposes a method for pre-disaster power outage risk assessment of a distribution network under a typhoon-rainstorm-flood disaster chain, which can effectively predict typhoon rainfall and flood water depth, comprehensively evaluate the power outage risk of the distribution network, and provide a scientific basis and effective suggestions for disaster prevention and mitigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic flowchart of a method for pre-disaster power outage risk assessment of a distribution network under a typhoon-rainstorm-flood disaster chain provided by an embodiment of the present application;

[0042] Figure 2 It is a flowchart of a one-dimensional-two-dimensional coupled flood risk analysis model provided by an embodiment of the present application;

[0043] Figure 3 It is a schematic diagram of the depth of waterlogging accumulation after the typhoon Talim makes landfall provided by an embodiment of the present application;

[0044] Figure 4 It is a schematic diagram of the driving force of each influencing factor on equipment power outage provided by an embodiment of the present application;

[0045] Figure 5 It is a diagram of the quantification result and distribution of the power outage risk of a typhoon disaster chain provided by an embodiment of the present application;

[0046] Figure 6 It is a schematic hardware structure diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments provided in the present application without creative efforts fall within the scope of protection of the present invention.

[0048] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. In addition, it can also be understood that although the efforts made in such a development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing, or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as insufficient disclosure of the content of the present application.

[0049] When the term "embodiment" is mentioned in this application, it means that the specific features, structures, or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0050] Unless otherwise defined, the technical terms or scientific terms involved in this application should have the ordinary meaning understood by those with ordinary skills in the technical field to which this application belongs. The words such as "a", "an", "one", "the" and the like involved in this application do not indicate a quantity limitation and can represent a singular or plural number. The terms "include", "comprise", "have" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device including a series of steps or modules (units) is not limited to the listed steps or units, but may further include steps or units not listed, or may further include other steps or units inherent to these processes, methods, products or devices. The terms "connect", "be connected", "couple" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plural" involved in this application means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0051] This application proposes a method for pre-disaster power outage risk assessment of distribution networks under the typhoon-rainstorm-flood disaster chain. First, a hybrid deep learning model is proposed to predict the rainfall time series within 48 hours after the typhoon makes landfall. Second, a one-dimensional hydrological and two-dimensional hydrodynamic coupled urban flood model is constructed to predict the typhoon flood water depth based on the rainfall time series. Third, an influencing factor set is constructed from the environmental and social perspectives, and the spatial correlation is used to quantify and evaluate the power outage risk of the distribution network. The method proposed in this application helps to formulate flood prevention strategies for the distribution network by analyzing the pre-disaster power outage risk of the distribution network under the typhoon-rainstorm-flood disaster chain.

[0052] As Figure 1 shown, this application proposes a method for pre-disaster power outage risk assessment of distribution networks under the typhoon-rainstorm-flood disaster chain, including the following steps:

[0053] Step 1: Predict the typhoon rainfall time series from a data-driven perspective based on a hybrid deep learning model.

[0054] Step 2: Construct a 1D-2D coupled rainstorm flood model for the study area, and use the predicted rainfall data as input to simulate the urban waterlogging situation under typhoon invasion from a physics-driven perspective.

[0055] Step 3: Use the geographical detector to evaluate the power outage risk in the power supply area of substation equipment from the environmental and social perspectives, and study the driving force of each influencing factor on the power outage.

[0056] Among them, the specific process of predicting the typhoon rainfall time series from a data-driven perspective based on the hybrid deep learning model in Step 1 is as follows:

[0057] Step 11: Read the meteorological data and geographical data of the study area, and perform normalization and equal-proportion scaling on the data to process it within the range of 0-1. The specific expression is:

[0058]

[0059] where: x′ is the normalized value; x i is the i-th input data; x min and x max are the minimum and maximum values of the input feature data, respectively.

[0060] Step 12: Input the meteorological data and geographical data normalized in Step 11 into the CNN-LSTM-XGBoost model based on the attention mechanism to obtain the typhoon rainstorm time series of the study area.

[0061] The specific process of constructing the 1D-2D coupled rainstorm flood model for the study area in Step 2 is as follows:

[0062] Step 21: Build a one-dimensional road confluence model. Use the Storm Water Management Model (SWMM) to establish a one-dimensional drainage pipe network. Input the surface roughness, surface cover type, characteristic width, Manning's N value, surface depression storage parameter, and the rainfall data predicted in Step 12 into the SWMM model to calculate the pipe network confluence. The specific steps are as follows:

[0063] (1) Use Thiessen polygons to divide sub-catchments for refined sub-catchment division and accurate parameter assignment. Calculate the Manning coefficient (i.e., Manning's N value) and sub-catchment parameters, and use ArcGIS software to associate the surface roughness, surface cover type, and Manning's N value (refer to the SWMM manual) with each sub-catchment.

[0064] The characteristic width is an important parameter affecting the surface runoff confluence time and peak flow. An accurate characteristic width helps to more realistically simulate the rainfall runoff process, including the prediction of runoff generation, confluence speed, and flood flow. Calculate the characteristic width of the sub-catchment, and the specific expression is as follows:

[0065]

[0066] In the formula, D width is the characteristic width of the sub-catchment; K is the model calibration parameter; is the area of the k-th sub-catchment.

[0067] (2) Input the rainfall data predicted in Step 12, as well as the surface roughness, surface cover type, Manning's N value, surface depression storage parameter, and characteristic width in Step 21 into the SWMM model to obtain the pipe network confluence in the study area.

[0068] The specific steps for evaluating the power outage risk in the power supply area of substation equipment in Step 3 are as follows:

[0069] Step 31: The geographical detector model is a statistical model for spatial analysis, mainly used to detect spatial stratification heterogeneity and reveal the driving forces behind it. Use the factor detection module in the geographical detector to determine the geographical weights of each disaster-causing factor. The dependent variable is the power outage time, and the specific expression is shown in the following formula:

[0070]

[0071] In the formula, W k ∈[0,1] is the driving force of the disaster-causing factor, and the larger its value, the stronger the explanatory power of the disaster-causing factor; h = 1,..., L is the partition of the study area; k is the k-th disaster-causing factor; N h and N are the number of units in area h and the total number of units in the study area, respectively; and σ 2They are the variance of the dependent variable in region h and the variance of the dependent variable in the entire region; V SSW and V SST are the sum of the variances of the partitions and the sum of the variances of the entire region, respectively.

[0072] Step 32: Using the driving forces of each factor obtained in Step 31 as weights, calculate the regional power outage risk under the typhoon-rainstorm-flood disaster chain through weighted average, and visualize the results of the distribution network risk analysis using ArcGIS Pro software.

[0073] The following combines Figures 1 to 5 to introduce the pre-disaster power outage risk assessment method for the distribution network under the typhoon-rainstorm-flood disaster chain of this application. Taking Xiasha District, Zhanjiang City, Guangdong Province, where Typhoon "Talim" landed in 2023 as an example for model simulation, the specific steps are as follows:

[0074] Step 1: Predict the typhoon rainfall time series from a data-driven perspective based on a hybrid deep learning model.

[0075] The specific method of predicting the typhoon rainfall time series from a data-driven perspective based on the hybrid deep learning model in Step 1 is as follows:

[0076] Step 11: Read the meteorological data and geographical data of the study area. Typhoon "Talim" landed on Nansan Island, Zhanjiang City at typhoon level (12 levels, 33 m / s). The maximum 10-minute average wind speed was 41.3 m / s, the maximum 3-second gust wind speed was 53.3 m / s, and the cumulative rainfall reached 228.9 mm (rainstorm level). The data was processed by normalizing and scaling proportionally to the range of 0-1. The specific expression is:

[0077]

[0078] where: x′ is the value after normalization; x i is the i-th input data; x min and x max are the minimum and maximum values of the input feature data, respectively. Among them, the characteristic variable x i and its value basis are shown in Table 1.

[0079] Table 1 Meteorological data and geographical data table

[0080]

[0081]

[0082] If there are multiple monitoring stations in the study area, the geographical data and meteorological data of all monitoring stations in the study area are used as input parameters for the hybrid deep learning model.

[0083] Step 12: Input the normalized meteorological and geographical data from Step 11 into the CNN-LSTM-XGBoost model based on the attention mechanism, and use the hybrid deep learning model to predict the short-term rainfall within 48 hours after the landfall of Typhoon Talim. Select geographical elevation, wind direction, average temperature, average wind speed, gust, relative humidity, surface cover type, longitude, latitude, slope, and aspect as feature variables for input, and use the rainfall time series as the output. Select the rainfall in other areas except the study area after the landfall of Typhoon Talim as the original training data set.

[0084] Step 2: Construct a 1D-2D coupled rainstorm and flood model for the study area, take the rainfall data predicted in Step 12 as the input, and simulate the urban waterlogging situation under the typhoon invasion from the perspective of physical driving.

[0085] As Figure 2 shown, the specific construction of the 1D-2D coupled rainstorm and flood model for the study area in Step 2 is as follows:

[0086] Step 21: Construct a one-dimensional road runoff model. Use the Storm Water Management Model (SWMM) to establish a one-dimensional drainage pipe network, input the surface roughness, surface cover type, characteristic width, surface depression storage parameter, Manning's N value, and the rainfall data predicted in Step 12 into the SWMM model, and calculate the pipe network runoff.

[0087] In the SWMM model, the pipe type is selected according to the national outdoor drainage design code. The main pipe uses a concrete buried pipe with a nominal diameter of 500 mm, a pipe length of 20 - 60 m, and a slope of 0.0025°. This type of pipe uses a socket rubber ring joint, the Manning coefficient inside the pipe is 0.013, the maximum flow velocity is 0.893 m / s, and the flow capacity is 175.312 L / s.

[0088] (1) Based on each power distribution and transformation equipment, use Thiessen polygons to divide sub-catchments for refined sub-catchment division and accurate parameter assignment. Use ArcGIS software to associate the surface roughness, surface cover type, and Manning's N value (refer to the SWMM manual) with each sub-catchment. The surface type classification of the sub-catchment sub-areas is shown in Table 2.

[0089] Table 2 Surface Type Classification Table of Sub-catchment Sub-areas

[0090]

[0091] To simplify the SWMM model, the flows in all branch pipes within the catchment area are concentrated into inspection wells and then flow into the main pipe. To reasonably simulate the ability of the pipe network to absorb surface water accumulation, the catchment area is divided into permeable areas and impermeable areas based on different underlying surface types, and the Manning coefficient is calculated. In this embodiment, referring to the SWMM model manual, the Manning coefficient is obtained by area-weighted averaging according to different underlying surface types in the catchment area. The surface types and Manning coefficients of a certain catchment area are shown in Table 3.

[0092] Table 3 Surface Types and Manning Coefficients of a Certain Catchment Area

[0093]

[0094] Similarly, referring to the SWMM model manual to calculate the surface depression storage parameter, in this embodiment, the sub-catchments S30, S31, and S32 are urban areas, the surface is mainly artificial structures, there are few permeable areas, the Manning coefficient is low, and the flood control ability is weak. Most of the sub-catchments S33 and S34 are fields and hillsides, and the Manning coefficient is high, so they have better water storage and flood control abilities. The parameter settings of some catchment areas are shown in Table 4.

[0095] Table 4 Parameter Settings of Some Catchment Areas

[0096]

[0097] The characteristic width is an important parameter affecting the surface runoff concentration time and peak flow. An accurate characteristic width helps to more realistically simulate the rainfall runoff process, including the prediction of runoff generation, concentration speed, and flood flow, etc. Calculate the characteristic width of the sub-catchment, and the specific expression is as follows:

[0098]

[0099] In the formula, D width is the characteristic width of the sub-catchment; K is the model calibration parameter; is the area of the k-th sub-catchment.

[0100] (2) Input the rainfall data predicted in step 12 and the surface roughness, surface cover type, Manning N value, surface depression storage parameter, and characteristic width in step 21 into the SWMM model to obtain the pipe network runoff in the study area.

[0101] Step 22: Use the InfoWorks ICM-2D module to establish a two-dimensional surface hydrodynamic model. Input the rainfall data predicted in step 12, as well as the information such as surface roughness, surface cover type, Manning N value, surface depression storage parameter, characteristic width, and traffic road network in step 21 into the InfoWorks ICM-2D module to simulate the flow direction and water accumulation process of the flood.

[0102] Step 23: Construct a one-dimensional and two-dimensional coupled typhoon rainstorm and flood prediction model. Through the dynamic coupling interface of InfoWorks ICM, real-time data interaction between the one-dimensional hydrodynamic model and the two-dimensional hydrodynamic model is realized. Integrate the pipe network confluence obtained in Step 21 and the flood flow direction and water accumulation process obtained in Step 22, and simulate the urban flood water accumulation under typhoon invasion from the perspective of physical driving to obtain the flood water accumulation depth after Typhoon Talim landed, as Figure 3 shown. The one-dimensional and two-dimensional water accumulation flow exchange formula is as follows:

[0103]

[0104] In the formula, Q n is the exchange flow between the one-dimensional pipe network and the two-dimensional surface; c0 is the overflow coefficient of the drain pipe outlet; c w is the weir flow coefficient; w is the perimeter of the drain manhole cover; A 1D-2D is the cross-sectional area for the pipe network and the surface to carry out flow exchange, that is, the area of the drain manhole cover; g is the gravity coefficient; h 1D , h 2D , and H respectively represent the water level of the one-dimensional pipe network node, the water level of the two-dimensional surface, and the surface elevation.

[0105] The established one-dimensional and two-dimensional coupled flood model covers 13 of the water accumulation points, and the coverage accuracy reaches 86.7% in the Typhoon Talim scenario. The maximum water accumulation depth reaches 1.62 m, and the area with a water depth above 1 m accounts for 0.79% of the total water accumulation area.

[0106] Step 3: Use the geographical detector to evaluate the power outage risk in the power supply area of substation equipment from the environmental and social perspectives, and study the driving force of each influencing factor on the power outage.

[0107] The specific steps for evaluating the power outage risk in the power supply area of substation equipment in Step 3 are as follows:

[0108] Step 31: The geographical detector model is a statistical model for spatial analysis, mainly used to detect spatial stratified heterogeneity and reveal the driving force behind it. There are 992 distribution and transformation equipment in the study area, and 116 of them are affected by flood disasters. According to the national electrical installation code, it is set that the water accumulation depth less than 0.2 m is a low risk, 0.2 - 0.5 m is a medium risk, and above 0.5 m is a high risk. According to the water accumulation depth of the study area obtained in Step 2, 49 pieces of equipment are in a high-risk waterlogging state, 14 are in a medium-risk state, and 43 are in a low-risk state. Use the geographic data processing tool in ArcGIS Pro to extract the disaster data at the locations of the equipment, including water depth (X1), population (X2), GDP (X3), precipitation (X4), temperature (X5), wind speed (X6), humidity (X7), gust (X8), elevation (X9), land use type (X10). Among them, the land use type is shown in Table 5.

[0109] Table 5 Land Use Type Table

[0110] Land use type Example Cultivated land Paddy field, dry land Forest land Arbor forest land, shrub forest land, bamboo forest land Grassland Natural grazing land, artificial grazing land Water areas and water conservancy facilities Rivers, lakes, reservoirs, ponds Construction land Urban residential, industrial land, roads Unused land Sandy land, saline-alkali land, bare rock and gravel land

[0111] The regional power outage time is the dependent variable (Y), and each influencing factor is the independent variable (X). As the input of the risk analysis model, the output is the driving force of each risk influencing factor on the power outage event. The specific expression is as follows:

[0112]

[0113] In the formula, W k ∈[0,1] is the driving force of the disaster-causing factor. The larger its value, the stronger the explanatory power of the disaster-causing factor; h = 1,…,L is the sub-region of the study area; k is the k-th disaster-causing factor; N h and N are the number of units in region h and the total number of units in the study area, respectively; and σ 2 are the variance of the dependent variable in region h and the variance of the dependent variable in the whole region, respectively; V SSW and V SST are the sum of the variances of the sub-regions and the sum of the variances of the whole region, respectively. Among them, the sub-region refers to the sub-watershed. For example, the population and GDP are the total population and GDP of the sub-watershed where the power transformation and distribution equipment is located.

[0114] The interaction matrix of each factor is shown in the table. The data on the diagonal of the matrix are the independent driving forces of each factor. Among them, the driving force of water depth (X1) is the highest (0.22), followed by gust (X8) at 0.16, and the driving force of relative wind speed (X6) is the lowest (0.03). The interaction matrix of each influencing factor is as Figure 4 and Table 6 show.

[0115] Table 6 Interaction Matrix Table of Each Influencing Factor

[0116]

[0117]

[0118] Step 32: Using the driving forces of each factor obtained in Step 31 as weights, calculate the regional power outage risk under the typhoon-rainstorm-flood disaster chain by weighted average, and visualize the results of the distribution network risk analysis through ArcGIS Pro software, as Figure 5 shown.

[0119] Among a total of 1,179 power transformation equipment, 80 are high-power outage risk equipment, accounting for 6.8% of the total; 324 are medium-high risk equipment, accounting for 27.5%. Affected by Typhoon "Talim", 8 actual power outage equipment are located in medium-high risk and high-risk areas. From the perspective of spatial distribution, although the southeastern part of the study area has a relatively low geographical elevation and poor drainage conditions, making it prone to waterlogging, due to the relatively low population and GDP, the impact of disasters is relatively small, so it is classified as a low-risk area. In contrast, the central part of the study area, as the commercial center and education center of Zhanjiang City, will cause economic losses of hundreds of thousands of yuan per hour in the event of a power outage. Therefore, the risk is relatively high when facing the typhoon disaster chain. It is particularly noteworthy that the southwestern part of the study area is Zhanjiang Railway Station. As an important transportation hub, the power supply reliability requirement is extremely high, and theoretically it should have strong disaster resistance capabilities. However, during this typhoon disaster, 2 power outage accidents still occurred within 1 kilometer around the railway station, exposing the vulnerability of the power supply network in this area. Therefore, although a relatively high fortification standard has been adopted in this area, under extreme weather conditions, its power outage risk is still relatively high and requires special attention and key protection.

[0120] In addition, combined with Figure 1 the power distribution network pre-disaster power outage risk assessment method described in the embodiments of the present application can be implemented by a computer device. Figure 6 It is a schematic diagram of the hardware structure of the computer device according to the embodiments of the present application. As Figure 6 shown, the device may include a processor 201 and a memory 202 storing computer program instructions.

[0121] Specifically, the above-mentioned processor 201 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0122] Among them, the memory 202 may include a mass storage for data or instructions. By way of example and not limitation, the memory 202 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In a suitable case, the memory 202 may include removable or non-removable (or fixed) media. In a suitable case, the memory 202 may be internal or external to the data processing device. In a particular embodiment, the memory 202 is a non-volatile memory. In a particular embodiment, the memory 202 includes a read-only memory (ROM) and a random access memory (RAM). In a suitable case, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. In a suitable case, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), where the DRAM may be a fast page mode dynamic random access memory (FPMDRAM), an extended date out dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0123] The memory 202 can be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 201.

[0124] The processor 201 reads and executes the computer program instructions stored in the memory 202 to implement any of the typhoon - rainstorm - flood disaster chain - based pre - disaster power outage risk assessment methods for distribution networks in the above embodiments.

[0125] In some embodiments, the point cloud generation device may further include a communication interface 203 and a bus 200. Among them, as Figure 6 shown, the processor 201, the memory 202, and the communication interface 203 are connected through the bus 200 and complete communication with each other.

[0126] The communication interface 203 is used to implement communication between the modules, devices, units, and / or devices in the embodiments of the present application. The communication interface 203 can also implement data communication with other components, such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations, etc.

[0127] The bus 200 includes hardware, software, or both, and couples the components of the point cloud generation device to each other. The bus 200 includes, but is not limited to, at least one of the following: Data Bus, Address Bus, Control Bus, Expansion Bus, Local Bus. By way of example and not limitation, the bus 200 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable bus or a combination of two or more of these. Where appropriate, the bus 200 may include one or more buses. Although the embodiments of the present application describe and illustrate specific buses, the present application contemplates any suitable bus or interconnect.

[0128] The computer device can execute the pre-disaster power outage risk assessment method for the distribution network under the typhoon-rainstorm-flood disaster chain in the embodiments of the present application based on the hydrological and hydrodynamic model, so as to achieve the combination Figure 1 of the pre-disaster power outage risk assessment method for the distribution network under the typhoon-rainstorm-flood disaster chain described.

[0129] In addition, in combination with the method for pre-disaster power outage risk assessment of the distribution network under the typhoon-rainstorm-flood disaster chain in the above embodiments, an embodiment of the present application can be implemented by providing a computer-readable storage medium. Computer program instructions are stored on the computer-readable storage medium; when the computer program instructions are executed by a processor, any one of the methods for pre-disaster power outage risk assessment of the distribution network under the typhoon-rainstorm-flood disaster chain in the above embodiments is implemented.

[0130] It should be noted that the technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification. In addition, according to the needs of implementation, each step / component described in the present application can be split into more steps / components, or two or more steps / components or partial operations of steps / components can be combined into new steps / components to achieve the purpose of the present invention.

[0131] Those skilled in the art can easily understand that the above-described embodiments only represent several implementation manners of the present application, and the description thereof is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, several deformations and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the appended claims.

Claims

1. A method for pre-disaster power outage risk assessment of a distribution network under the typhoon-rainstorm-flood disaster chain, characterized in that, The method includes: Predicting the typhoon rainfall time series of the target area from a data-driven perspective based on a hybrid deep learning model; Constructing a 1D-2D coupled rainstorm and flood model for the target area, using the typhoon rainfall time series as input, and simulating the urban waterlogging situation under typhoon invasion from a physically driven perspective to obtain the floodwater depth after the typhoon makes landfall; Using a geographical detector to evaluate the power distribution and transformation equipment power outage risk from environmental and social perspectives, determining the driving forces of each environmental factor and social factor on the power outage event, using the driving forces of each factor as weights, and calculating the power distribution and transformation equipment power outage risk under the typhoon-rainstorm-flood disaster chain by weighted average; among them, the environmental factors include the floodwater depth.

2. The method for pre-disaster power outage risk assessment of a distribution network under the typhoon-rainstorm-flood disaster chain according to claim 1, wherein, Predicting the typhoon rainfall time series of the target area from a data-driven perspective based on a hybrid deep learning model, including: Obtaining the meteorological data and geographical data of the target area and performing data preprocessing; Inputting the preprocessed meteorological data and geographical data into the hybrid deep learning model to predict the typhoon rainfall time series of the target area.

3. The pre-disaster power outage risk assessment method for distribution networks under the typhoon-rainstorm-flood disaster chain according to claim 2, characterized in that The meteorological data includes average wind speed, wind direction, gust, average temperature, and relative humidity, the geographical data includes geographical elevation, slope, aspect, land cover type, longitude, and latitude, the data preprocessing is data normalization, and the hybrid deep learning model is a CNN-LSTM-XGBoost model based on an attention mechanism.

4. The method for pre-disaster power outage risk assessment of a distribution network under the typhoon-rainstorm-flood disaster chain according to claim 1, wherein Constructing a 1D-2D coupled rainstorm and flood model for the target area, using the typhoon rainfall time series as input, and simulating the urban waterlogging situation under typhoon invasion from a physically driven perspective to obtain the floodwater depth after the typhoon makes landfall, including: Constructing a one-dimensional road runoff model, that is, using the Storm Water Management Model (SWMM) to establish a one-dimensional drainage pipe network, and inputting surface roughness, land cover type, characteristic width, Manning's n value, surface depression storage parameter, and typhoon rainfall time series to calculate the pipe network runoff; Using the InfoWorks ICM-2D module to establish a two-dimensional surface water dynamics model, and inputting surface roughness, land cover type, characteristic width, Manning's n value, surface depression storage parameter, traffic road network, and typhoon rainfall time series to simulate the surface flood flow direction and water accumulation process; Realize the real-time data interaction between the one-dimensional road runoff model and the two-dimensional surface water dynamics model through the dynamic coupling interface of InfoWorks ICM, so as to integrate the pipe network runoff with the surface flood flow direction and water accumulation process, construct a one-dimensional-two-dimensional coupled typhoon rainstorm and flood prediction model, and simulate the urban flood waterlogging situation under typhoon invasion from a physically driven perspective to obtain the floodwater depth after the typhoon makes landfall.

5. The pre-disaster power outage risk assessment method for distribution networks under the typhoon-rainstorm-flood disaster chain according to claim 4, wherein, The one-dimensional-two-dimensional water accumulation flow exchange formula is as follows: Where, Q n is the exchange flow between the one-dimensional road confluence model and the two-dimensional surface water dynamics model; c0 is the overflow coefficient of the drain pipe outlet; c w is the weir flow coefficient; w is the perimeter of the drain manhole; A 1D-2D is the cross-sectional area for the flow exchange between the pipe network and the surface, i.e., the area of the drain manhole; g is the gravity coefficient; h 1D , h 2D , H respectively represent the water level of the one-dimensional drainage pipe network node, the two-dimensional surface water level and the surface elevation.

6. The pre-disaster power outage risk assessment method for distribution networks under the typhoon-rainstorm-flood disaster chain according to claim 4, wherein Constructing a one-dimensional road runoff model, specifically including: Based on all the power distribution and transformation equipment in the target area, using Thiessen polygons to divide the target area into several sub-catchments, and using ArcGIS software to associate surface roughness, land cover type, and Manning's n value with each sub-catchment; Dividing the sub-catchments into infiltration areas and impervious areas based on different underlying surface types, and calculating the Manning's n value of each sub-catchment by area-weighted average according to the area of different underlying surface types in the sub-catchments. Calculate the surface depression storage parameters of each sub-catchment area; Calculate the characteristic width of the sub-catchment area, and the specific expression is as follows: where D width is the characteristic width of the sub - catchment; K is the model calibration parameter; is the area of the k - th sub - catchment; Input the surface roughness, surface cover type, characteristic width, Manning's N value, surface depression storage parameters, and typhoon rainfall time series into the one-dimensional drainage pipe network SWMM model to calculate the pipe network runoff in the target area.

7. The method for pre-disaster power outage risk assessment of distribution network under typhoon-rainstorm-flood disaster chain according to claim 6, wherein The surface cover types of the sub-catchment area are divided into permeable areas and impermeable areas. The permeable areas include forest land, grassland, water area, cultivated land, and natural bare land, and the impermeable areas include housing buildings, roads, and artificial bare land; The underlying surface types of the sub-catchment area are divided into permeable surfaces, impermeable surfaces, and others. The permeable surfaces include cultivated land, forest land, grassland, and natural bare land, the impermeable surfaces include artificial surfaces, and the others include water areas and wetlands.

8. The method for pre-disaster power outage risk assessment of a distribution network under a typhoon-rainstorm-flood disaster chain according to claim 1, wherein, Use the geographical detector to evaluate the power distribution and transformation equipment outage risk from the environmental and social perspectives, and determine the driving forces of each environmental factor and social factor on the outage event. Using the driving forces of each factor as weights, calculate the power distribution and transformation equipment outage risk under the typhoon-rainstorm-flood disaster chain, including: Use the geographical data processing tools in ArcGIS Pro to extract the environmental factors and social factors at the locations of each power distribution and transformation equipment; among them, the environmental factors include floodwater depth, rainfall, average temperature, wind speed, relative humidity, gust, geographical elevation, and land use type; the social factors include population and GDP; Regarding each factor as an independent variable and the power distribution and transformation equipment outage time as the dependent variable, use the factor detection module in the geographical detector to determine the driving force of each factor, and the expression is as shown in the following formula: where W k ∈[0,1] is the driving force of each factor, and the larger its value, the stronger the explanatory power of the factor; h = 1, …, L is the target area partition; k is the k-th factor; N h and N are the number of units in area h and the total number of units in the target area, respectively; and σ 2 are the variance of the dependent variable in area h and the variance of the dependent variable in the entire area, respectively; V SSW and V SST are the sum of the variances of the partitions and the sum of the variances of the entire area, respectively; Using the driving forces of each factor as weights, calculate the power distribution and transformation equipment outage risk under the typhoon-rainstorm-flood disaster chain by weighted average.

9. An electronic device, characterized in that Including: A processor and a memory, and the memory stores a program or instruction that can run on the processor. When the program or instruction is executed by the processor, the steps of the power distribution network pre-disaster outage risk assessment method under the typhoon-rainstorm-flood disaster chain described in any one of claims 1 to 8 are implemented.

10. A readable storage medium, characterized in that, A program or instruction is stored thereon, and when the program or instruction is executed by the processor, the steps of the power distribution network pre-disaster outage risk assessment method under the typhoon-rainstorm-flood disaster chain described in any one of claims 1 to 8 are implemented.

Images