Network key asset micro-grid risk mapping method and device, computer equipment, storage medium and computer program product

Abstract

This application relates to a method, apparatus, computer equipment, storage medium, and computer program product for microgrid risk mapping of key assets in a distribution network. The method includes: acquiring cumulative rainfall, total cloud cover, and surface shortwave radiation values ​​of a low-voltage distribution network grid, as well as first asset data for substation assets and second asset data for photovoltaic (PV) power plant assets within the grid; determining the waterlogging index of substation assets based on cumulative rainfall and first asset data; determining the effective irradiance value of PV power plant assets based on cumulative rainfall, total cloud cover, surface shortwave radiation value, and second asset data; determining the output attenuation rate of PV power plant assets based on the effective irradiance value; identifying target distribution network grids that meet preset conditions from each grid based on the waterlogging index and output attenuation rate; and generating a risk mapping result for the low-voltage distribution network based on the grid risk level of the target distribution network grid. Using this method can improve the accuracy of risk identification in low-voltage distribution networks.

Description

Technical Field

[0001] This application relates to the field of power grid technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for microgrid risk mapping of key assets in distribution networks. Background Technology

[0002] With the explosive growth of distributed renewable energy in new power systems and the digital transformation of distribution networks, accurate risk identification of low-voltage distribution networks is crucial to ensuring the reliability of power supply.

[0003] In traditional technologies, risk identification for low-voltage distribution networks is generally based on a single factor. However, this approach only assesses a single type of distribution network risk and cannot effectively couple the synergistic disaster impacts of substation flooding and photovoltaic power output degradation. This can easily lead to large risk identification biases and result in low accuracy of risk identification for low-voltage distribution networks. Summary of the Invention

[0004] Based on this, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for microgrid risk mapping of key assets in distribution networks that can improve the accuracy of risk identification in low-voltage distribution networks, addressing the aforementioned technical problems.

[0005] Firstly, this application provides a microgrid risk mapping method for key assets in a distribution network, including:

[0006] Acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as first asset data of substation assets and second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size;

[0007] Based on the cumulative rainfall and the first asset data, the waterlogging index of the substation asset is determined, and based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station asset is determined.

[0008] Based on the effective irradiance value, the output attenuation rate of the photovoltaic power station asset is determined;

[0009] Based on the waterlogging index and the power output attenuation rate, target distribution grids that meet preset conditions are determined from each of the distribution grids;

[0010] Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0011] In one embodiment, determining the target distribution grid that meets preset conditions from each of the distribution grids based on the waterlogging index and the power output attenuation rate includes:

[0012] From each of the distribution network grids, a redundant distribution network grid is identified where the waterlogging index is equal to the preset waterlogging index and the power output attenuation rate is less than the preset power output attenuation rate.

[0013] The redundant distribution network grid is deleted from the distribution network grid to obtain the target distribution network grid that meets the preset conditions.

[0014] In one embodiment, obtaining the grid risk level of the target distribution network grid includes:

[0015] Based on the waterlogging index of the substation assets in the target distribution network grid, the first risk value of the target distribution network grid is determined, and based on the power output attenuation rate of the photovoltaic power station assets in the target distribution network grid, the second risk value of the target distribution network grid is determined.

[0016] The first risk value and the second risk value are fused together to obtain the fused risk value of the target distribution network grid;

[0017] Based on the fusion risk value, the grid risk level of the target distribution network grid is determined.

[0018] In one embodiment, determining the flooding index of the substation asset based on the cumulative rainfall and the first asset data includes:

[0019] From the first asset data, the critical rainfall threshold of the substation asset is extracted;

[0020] If the cumulative rainfall is less than or equal to the critical rainfall threshold, the waterlogging index of the substation asset is determined to be the preset waterlogging index;

[0021] If the cumulative rainfall exceeds the critical rainfall threshold, the flooding index of the substation asset is determined based on the cumulative rainfall and the critical rainfall threshold.

[0022] In one embodiment, determining the effective irradiance of the photovoltaic power station asset based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data includes:

[0023] The irradiance conversion coefficient of the photovoltaic power station asset is extracted from the second asset data;

[0024] The initial irradiance of the photovoltaic power station asset is determined based on the total cloud cover, the surface shortwave radiation value, and the irradiance conversion coefficient.

[0025] Based on the cumulative rainfall, the initial irradiance value is adjusted to obtain the effective irradiance value of the photovoltaic power station asset.

[0026] In one embodiment, acquiring the grid meteorological data of the low-voltage distribution network grid includes:

[0027] The initial distribution grid corresponding to the low-voltage distribution network is determined; the grid size of the initial distribution grid is larger than the preset size;

[0028] Obtain the meteorological data and corner coordinates of the reference grid corresponding to the four corners of the initial distribution network grid;

[0029] Obtain the relative coordinates of the distribution network grid in the initial distribution network grid, and perform bilinear interpolation on the reference grid meteorological data based on the corner coordinates and the relative coordinates to obtain the grid meteorological data of the distribution network grid.

[0030] Secondly, this application also provides a microgrid risk mapping device for key assets in a distribution network, comprising:

[0031] The data acquisition module is used to acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as the first asset data of the substation assets and the second asset data of the photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size;

[0032] The data determination module is used to determine the waterlogging index of the substation asset based on the cumulative rainfall and the first asset data, and to determine the effective irradiance value of the photovoltaic power station asset based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value and the second asset data.

[0033] The attenuation rate determination module is used to determine the output attenuation rate of the photovoltaic power station asset based on the effective irradiance value.

[0034] The grid determination module is used to determine the target distribution grid that meets the preset conditions from each of the distribution grids based on the waterlogging index and the power output attenuation rate.

[0035] The result generation module is used to obtain the grid risk level of the target distribution network grid and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0036] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0037] Acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as first asset data of substation assets and second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size;

[0038] Based on the cumulative rainfall and the first asset data, the waterlogging index of the substation asset is determined, and based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station asset is determined.

[0039] Based on the effective irradiance value, the output attenuation rate of the photovoltaic power station asset is determined;

[0040] Based on the waterlogging index and the power output attenuation rate, target distribution grids that meet preset conditions are determined from each of the distribution grids;

[0041] Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0042] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0043] Acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as first asset data of substation assets and second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size;

[0044] Based on the cumulative rainfall and the first asset data, the waterlogging index of the substation asset is determined, and based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station asset is determined.

[0045] Based on the effective irradiance value, the output attenuation rate of the photovoltaic power station asset is determined;

[0046] Based on the waterlogging index and the power output attenuation rate, target distribution grids that meet preset conditions are determined from each of the distribution grids;

[0047] Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0048] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0049] Acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as first asset data of substation assets and second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size;

[0050] Based on the cumulative rainfall and the first asset data, the waterlogging index of the substation asset is determined, and based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station asset is determined.

[0051] Based on the effective irradiance value, the output attenuation rate of the photovoltaic power station asset is determined;

[0052] Based on the waterlogging index and the power output attenuation rate, target distribution grids that meet preset conditions are determined from each of the distribution grids;

[0053] Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0054] The aforementioned method, device, computer equipment, storage medium, and computer program product for microgrid risk mapping of key assets in the distribution network first acquires the grid meteorological data of the distribution network grids in the low-voltage distribution network, as well as the first asset data of substation assets and the second asset data of photovoltaic power station assets within the distribution network grids. The grid meteorological data includes at least the cumulative rainfall, total cloud cover, and surface shortwave radiation value of the distribution network grids. The grid size of the distribution network grids is smaller than a preset size. Then, based on the cumulative rainfall and the first asset data, the waterlogging index of the substation assets is determined. Based on the cumulative rainfall, total cloud cover, surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station assets is determined. Next, based on the effective irradiance value, the output attenuation rate of the photovoltaic power station assets is determined. Then, based on the waterlogging index and the output attenuation rate, the target distribution network grids that meet the preset conditions are determined from each distribution network grid. Finally, the grid risk level of the target distribution network grids is obtained, and the risk mapping result of the low-voltage distribution network is generated based on the grid risk level. In this way, when identifying risks in low-voltage distribution networks, by acquiring grid meteorological data including cumulative rainfall, total cloud cover, and surface shortwave radiation values ​​under small-sized distribution network grids, as well as substation primary asset data and photovoltaic power station secondary asset data, the substation waterlogging index is calculated based on cumulative rainfall combined with substation asset data. Then, by integrating cumulative rainfall, total cloud cover, surface shortwave radiation, and photovoltaic asset data, the effective irradiance value of photovoltaics is solved, and the photovoltaic power output attenuation rate is further derived. Simultaneously, the two related disaster indicators of substation waterlogging and photovoltaic power output attenuation are quantified, overcoming the shortcomings of traditional single-factor judgment models that cannot couple the synergistic effects of the two types of disasters. By combining the two indicators to screen target distribution network grids and matching the corresponding grid risk levels to generate an overall risk mapping result, the synergistic disaster effects of waterlogging and photovoltaic power output attenuation are comprehensively considered, thereby eliminating the risk identification bias caused by single-factor judgment and improving the accuracy of risk identification in low-voltage distribution networks. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a flowchart illustrating a microgrid risk mapping method for key assets in a power distribution network in one embodiment.

[0057] Figure 2 This is a flowchart illustrating the microgrid risk mapping method for key assets in a distribution network in another embodiment;

[0058] Figure 3This is a flowchart illustrating the microgrid risk mapping method for key assets in a distribution network in yet another embodiment;

[0059] Figure 4 This is a schematic diagram of a full-process control architecture for disaster prevention of distribution network assets based on microgrid multi-layer overlay in one embodiment;

[0060] Figure 5 This is a structural block diagram of a microgrid risk mapping device for key assets in a power distribution network in one embodiment;

[0061] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0063] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0064] In one exemplary embodiment, such as Figure 1 As shown, a microgrid risk mapping method for key assets in a distribution network is provided. This embodiment illustrates the method by applying it to a server. It is understood that this method can also be applied to terminals, and to systems including terminals and servers, and is implemented through interaction between the terminals and servers. The terminals can be, but are not limited to, various personal computers, laptops, smartphones, and tablets; the servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing cloud computing services. In this embodiment, the method includes the following steps:

[0065] Step S101: Obtain the grid meteorological data of the distribution grid of the low-voltage distribution network, as well as the first asset data of the substation assets and the second asset data of the photovoltaic power station assets in the distribution grid; the grid meteorological data shall include at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid shall be smaller than the preset size.

[0066] Low-voltage distribution networks refer to power distribution networks with voltage levels of 10kV and below that directly supply power to users.

[0067] Among them, the distribution network grid, also known as the microgrid of the low-voltage distribution network, refers to the square geographical grid unit obtained by uniformly dividing the geographical area covered by the low-voltage distribution network.

[0068] Among them, substation assets refer to step-down substations deployed within the power supply coverage area of ​​the low-voltage distribution network.

[0069] The first asset data refers to the static ledger data of the substation assets, which includes at least the substation's specific critical rainfall threshold (the maximum safe cumulative rainfall that the substation can withstand), the substation's GPS (Global Positioning System) geographic coordinates, and historical water accumulation fault records.

[0070] Among them, photovoltaic power station assets refer to new energy power generation equipment such as distributed photovoltaic arrays, photovoltaic inverters, and transformer substations connected to low-voltage distribution networks.

[0071] The second asset data refers to the static ledger data of photovoltaic power station assets, which includes at least the photovoltaic power station's exclusive irradiance conversion coefficient, rated photovoltaic installed capacity, and the station's GPS coordinates.

[0072] The cumulative rainfall refers to the total cumulative rainfall in the area of ​​the distribution network grid within the preset warning period, expressed in millimeters, and is specifically calculated from the radar pixels of the distribution network grid.

[0073] The total cloud cover refers to the percentage of cloud coverage in the area corresponding to the distribution grid, with a value ranging from 0 to 1.

[0074] Among them, the surface shortwave radiation value refers to the theoretically maximum solar shortwave irradiance intensity that the surface of the distribution network can receive, and the unit is 1000 ppm. .

[0075] Among them, the grid size refers to the length of a single side of the square grid cell of the distribution network, which is used to characterize the grid spatial resolution of the distribution network.

[0076] The preset size refers to the pre-set size threshold. In the actual scenario, the side length of the traditional meteorological coarse grid used as a comparison benchmark is fixed at 25km (corresponding to the 0.25° original forecast grid in the meteorological field). The grid size of this application is smaller than the preset size, preferably 1km×1km.

[0077] For example, in response to a risk mapping instruction for a low-voltage distribution network, the server determines the geographical area covered by the low-voltage distribution network based on a regional power GIS (Geographic Information System) system, and uniformly divides the geographical area covered by the low-voltage distribution network to obtain the distribution network grid of the low-voltage distribution network. Then, through a weather forecast service interface, the server obtains the cumulative rainfall, total cloud cover, and surface shortwave radiation value of the distribution network grid of the low-voltage distribution network according to a preset time step (6-minute update interval, for a total of 12 consecutive frames) as the grid meteorological data of the distribution network grid. In addition, the server reads the first asset data of substation assets and the second asset data of photovoltaic power station assets in the distribution network grid through the power asset ledger database. The grid size of the distribution network grid is smaller than the preset size.

[0078] Step S102: Based on the cumulative rainfall and the first asset data, determine the waterlogging index of the substation asset; based on the cumulative rainfall, total cloud cover, surface shortwave radiation value, and the second asset data, determine the effective irradiance value of the photovoltaic power station asset.

[0079] The waterlogging index is used to indicate the degree of risk associated with water accumulation and flooding in substation assets.

[0080] Among them, the effective irradiance value is used to represent the actual solar shortwave irradiance intensity that photovoltaic power station assets can receive and use for photoelectric conversion under the influence of meteorological factors such as clouds or rainfall.

[0081] For example, the server inputs the cumulative rainfall and the first asset data into a pre-built waterlogging index determination model to obtain the waterlogging index of the substation asset; then, it inputs the cumulative rainfall, total cloud cover, surface shortwave radiation value, and the second asset data into a pre-built effective irradiance value determination model to determine the effective irradiance value of the photovoltaic power station asset.

[0082] Step S103: Determine the output degradation rate of the photovoltaic power station assets based on the effective irradiance value.

[0083] Among them, the output attenuation rate is used to represent the percentage decrease in the effective irradiance of photovoltaic power station assets relative to the clear-sky baseline irradiance.

[0084] Among them, the clear-sky baseline irradiance value is used to represent the theoretical maximum shortwave solar irradiance that photovoltaic power station assets can receive under the condition that there are no meteorological factors such as clouds and rainfall.

[0085] For example, the server obtains the clear-sky reference irradiance value of the photovoltaic power station asset; then, it performs a subtraction operation on the clear-sky reference irradiance value and the effective irradiance value to obtain the irradiance difference value; then, the ratio between the irradiance difference value and the clear-sky reference irradiance value is used as the output degradation rate of the photovoltaic power station asset.

[0086] Step S104: Based on the waterlogging index and power output attenuation rate, determine the target distribution grid that meets the preset conditions from each distribution grid.

[0087] Among them, the preset conditions refer to the judgment criteria set for screening distribution network grids with power supply risks.

[0088] The target distribution grid refers to the distribution grid that meets the preset conditions.

[0089] For example, the server determines the redundant distribution grids in the distribution grid based on the waterlogging index and the power output attenuation rate; then, it deletes the redundant distribution grids from the distribution grid to obtain the target distribution grid that meets the preset conditions.

[0090] Step S105: Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0091] Among them, the grid risk level is used to represent the overall risk level of the target distribution network grid, such as low risk, medium risk, high risk, and extremely high risk.

[0092] Among them, the risk mapping result refers to the output result formed after spatially visually mapping the grid risk level corresponding to the target distribution grid.

[0093] For example, the server determines the grid risk level of the target distribution grid based on the waterlogging index of substation assets in the target distribution grid and the output attenuation rate of photovoltaic power station assets in the target distribution grid; then, based on the grid risk level, it queries the correspondence between the risk level and the mapping method to obtain the mapping method corresponding to the grid risk level; then, according to the mapping method corresponding to the grid risk level, it performs the corresponding mapping processing on the target distribution grid to obtain the risk mapping result of the low-voltage distribution network.

[0094] In the aforementioned microgrid risk mapping method for key assets of the distribution network, the following steps are taken: First, the grid meteorological data of the distribution network grids of the low-voltage distribution network, as well as the first asset data of substation assets and the second asset data of photovoltaic power station assets within the distribution network grids, are obtained. The grid meteorological data includes at least the cumulative rainfall, total cloud cover, and surface shortwave radiation value of the distribution network grids. The grid size of the distribution network grids is smaller than a preset size. Then, based on the cumulative rainfall and the first asset data, the waterlogging index of the substation assets is determined. Based on the cumulative rainfall, total cloud cover, surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station assets is determined. Next, based on the effective irradiance value, the output attenuation rate of the photovoltaic power station assets is determined. Then, based on the waterlogging index and the output attenuation rate, the target distribution network grids that meet the preset conditions are determined from each distribution network grid. Finally, the grid risk level of the target distribution network grids is obtained, and the risk mapping result of the low-voltage distribution network is generated based on the grid risk level. In this way, when identifying risks in low-voltage distribution networks, by acquiring grid meteorological data including cumulative rainfall, total cloud cover, and surface shortwave radiation values ​​under small-sized distribution network grids, as well as substation primary asset data and photovoltaic power station secondary asset data, the substation waterlogging index is calculated based on cumulative rainfall combined with substation asset data. Then, by integrating cumulative rainfall, total cloud cover, surface shortwave radiation, and photovoltaic asset data, the effective irradiance value of photovoltaics is solved, and the photovoltaic power output attenuation rate is further derived. Simultaneously, the two related disaster indicators of substation waterlogging and photovoltaic power output attenuation are quantified, overcoming the shortcomings of traditional single-factor judgment models that cannot couple the synergistic effects of the two types of disasters. By combining the two indicators to screen target distribution network grids and matching the corresponding grid risk levels to generate an overall risk mapping result, the synergistic disaster effects of waterlogging and photovoltaic power output attenuation are comprehensively considered, thereby eliminating the risk identification bias caused by single-factor judgment and improving the accuracy of risk identification in low-voltage distribution networks.

[0095] In an exemplary embodiment, step S104 above, which determines the target distribution grid that meets the preset conditions from each distribution grid based on the waterlogging index and the power output attenuation rate, specifically includes the following: determining redundant distribution grids from each distribution grid whose waterlogging index is equal to the preset waterlogging index and whose power output attenuation rate is less than the preset power output attenuation rate; deleting the redundant distribution grids from the distribution grids to obtain the target distribution grid that meets the preset conditions.

[0096] The preset flooding index is a benchmark value used to determine whether a substation is at risk of flooding, such as 0.

[0097] The preset power attenuation rate refers to the critical percentage threshold used to determine that a photovoltaic power station has no significant risk of power attenuation, such as 10%.

[0098] Redundant distribution grids refer to distribution grids that do not pose a risk.

[0099] For example, the server identifies distribution grids from each distribution grid that have a constant flooding index of 0 and an output attenuation rate of less than 10%, and designates them as redundant distribution grids; then, the redundant distribution grids are removed from the distribution grids to obtain target distribution grids that meet preset conditions.

[0100] In this embodiment, redundant distribution network grids with waterlogging indices equal to the preset waterlogging index and power output attenuation rates less than the preset power output attenuation rate are identified and eliminated simultaneously. Only target distribution network grids with substation waterlogging risk or photovoltaic power output attenuation risk are retained for subsequent comprehensive risk calculation. This avoids interference from risk-free grids with risk classification results, which helps to improve the pertinence and evaluation efficiency of comprehensive risk identification of low-voltage distribution networks.

[0101] In an exemplary embodiment, step S105 above, obtaining the grid risk level of the target distribution grid, specifically includes the following: determining the first risk value of the target distribution grid based on the waterlogging index of the substation assets in the target distribution grid; determining the second risk value of the target distribution grid based on the output attenuation rate of the photovoltaic power station assets in the target distribution grid; merging the first risk value and the second risk value to obtain the merged risk value of the target distribution grid; and determining the grid risk level of the target distribution grid based on the merged risk value.

[0102] The first risk value refers to the risk value obtained based on the waterlogging index of substation assets in the target distribution network grid.

[0103] The second risk value refers to the risk value obtained based on the output degradation rate of photovoltaic power station assets in the target distribution grid.

[0104] Among them, the fusion risk value refers to the risk value obtained by merging the first risk value and the second risk value.

[0105] For example, the server extracts the waterlogging index of substation assets in the target distribution network grid from the waterlogging index of substation assets in the distribution network grid, and extracts the output attenuation rate of photovoltaic power station assets in the target distribution network grid from the output attenuation rate of photovoltaic power station assets in the distribution network grid. Then, the waterlogging index of substation assets in the target distribution network grid is input into the trained risk prediction model to obtain the first risk value of the target distribution network grid, and the output attenuation rate of photovoltaic power station assets in the target distribution network grid is input into the trained risk prediction model to obtain the second risk value of the target distribution network grid. Then, the first weight corresponding to the first risk value and the second weight corresponding to the second risk value are obtained, and the first risk value and the second risk value are summed according to the first weight and the second weight to obtain the merged risk value of the target distribution network grid. Then, based on the merged risk value, the correspondence between the risk value and the risk level is queried to obtain the risk level corresponding to the merged risk value, which is used as the grid risk level of the target distribution network grid.

[0106] In this embodiment, different risk values ​​are calculated based on the waterlogging index and the power output attenuation rate, respectively. Then, the two types of risk values ​​are fused to obtain a fused risk value, and the grid risk level is divided accordingly. This enables a unified quantitative assessment of risks in different dimensions, breaking the limitations of traditional single-risk assessment and providing a hierarchical basis for generating full-domain visualized risk mapping results.

[0107] In an exemplary embodiment, step S102 above, which determines the waterlogging index of the substation asset based on the cumulative rainfall and the first asset data, specifically includes the following: extracting the critical rainfall threshold of the substation asset from the first asset data; determining the waterlogging index of the substation asset as a preset waterlogging index when the cumulative rainfall is less than or equal to the critical rainfall threshold; and determining the waterlogging index of the substation asset based on the cumulative rainfall and the critical rainfall threshold when the cumulative rainfall is greater than the critical rainfall threshold.

[0108] Among them, the critical rainfall threshold refers to the pre-set cumulative rainfall threshold.

[0109] The preset flooding index refers to a pre-set flooding index, such as 0.

[0110] For example, the server inputs the first asset data into the trained data extraction model. Through the trained data extraction model, the critical rainfall threshold of the substation asset is extracted from the first asset data. Then, if the cumulative rainfall is less than or equal to the critical rainfall threshold, the substation asset's waterlogging index is determined as a preset waterlogging index. If the cumulative rainfall is greater than the critical rainfall threshold, the cumulative rainfall and the critical rainfall threshold are divided, and the resulting quotient is input into the pre-built waterlogging index determination model to obtain the substation asset's waterlogging index.

[0111] The waterlogging index can be calculated using the following formula:

[0112] Equation (1)

[0113] in, This refers to the waterlogging index of substation k in the nth statistical period. To predict the discrete frame number nodes corresponding to the timeliness, This is a discrete time step constant (e.g., 6 minutes). This refers to the distribution network grid to which substation k belongs. The cumulative rainfall obtained by summing up over n consecutive time periods. This refers to the critical rainfall threshold. This refers to the radar physical conversion coefficient. It refers to a grid No. Rainfall intensity was retrieved by radar over a specific time period.

[0114] In this embodiment, the waterlogging index is calculated in layers based on the relationship between the critical rainfall threshold and the cumulative rainfall of substation assets. This allows for a more refined risk assessment that aligns with the differentiated flood control capacity of different substations, avoiding the assessment bias caused by uniform standards. As a result, the degree of water accumulation hazard in substations can be clearly and quantitatively reflected.

[0115] In an exemplary embodiment, step S102 above, which determines the effective irradiance value of the photovoltaic power station asset based on the cumulative rainfall, total cloud cover, surface shortwave radiation value, and second asset data, specifically includes the following: extracting the irradiance conversion coefficient of the photovoltaic power station asset from the second asset data; determining the initial irradiance value of the photovoltaic power station asset based on the total cloud cover, surface shortwave radiation value, and irradiance conversion coefficient; and adjusting the initial irradiance value based on the cumulative rainfall to obtain the effective irradiance value of the photovoltaic power station asset.

[0116] Among them, the irradiance conversion factor refers to the conversion factor used by photovoltaic power station assets to convert the regional surface shortwave radiation into the actual irradiance received by the photovoltaic panels.

[0117] The initial irradiance value refers to the irradiance value calculated based on the total cloud cover, surface shortwave radiation value, and irradiance conversion coefficient.

[0118] For example, the server inputs the second asset data into a trained data extraction model, and extracts the irradiance conversion coefficient of the photovoltaic power station asset from the second asset data through the trained data extraction model. Then, the total cloud cover, surface shortwave radiation value, and irradiance conversion coefficient are input into a pre-built irradiance value determination model to obtain the initial irradiance value of the photovoltaic power station asset. Then, based on the cumulative rainfall, the correspondence between rainfall and adjustment coefficient is queried to obtain the adjustment coefficient corresponding to the cumulative rainfall, which is used as the target adjustment coefficient corresponding to the initial irradiance value. Finally, the target adjustment coefficient is multiplied by the initial irradiance value to obtain the effective irradiance value of the photovoltaic power station asset.

[0119] The effective irradiance value can be calculated using the following formula:

[0120] Equation (2)

[0121] in, This refers to the effective irradiance value of the j-th photovoltaic power station at time t. This refers to the irradiance conversion coefficient corresponding to photovoltaic power station j. This refers to the distribution grid to which photovoltaic power station j belongs. The surface shortwave radiation value at time t It refers to a grid Total cloud cover at time t This refers to the fixed coefficient of rainfall attenuation. Refers to grid Rainfall intensity measured by radar at time t.

[0122] In this embodiment, the initial irradiance value is calculated based on the irradiance conversion coefficient of the photovoltaic power station assets, combined with the total cloud cover and surface shortwave radiation value in the region, considering only cloud shading loss. Then, the initial irradiance value is adjusted a second time by introducing raindrop scattering attenuation correction based on the cumulative rainfall in the grid, so as to obtain the effective irradiance value. This is conducive to improving the accuracy and pertinence of photovoltaic risk assessment.

[0123] In an exemplary embodiment, step S101, obtaining the grid meteorological data of the distribution grid of the low-voltage distribution network, specifically includes the following: determining the initial distribution grid corresponding to the low-voltage distribution network; the grid size of the initial distribution grid is larger than a preset size; obtaining the reference grid meteorological data and corner coordinate values ​​corresponding to the four corners of the initial distribution grid; obtaining the relative coordinate values ​​of the distribution grid in the initial distribution grid; and performing bilinear interpolation on the reference grid meteorological data based on the corner coordinate values ​​and the relative coordinate values ​​to obtain the grid meteorological data of the distribution grid.

[0124] The initial distribution grid refers to the coarse-scale grid corresponding to the low-voltage distribution network, with a grid size of 25km.

[0125] Among them, the four corners of the grid refer to the four vertex positions of the rectangular boundary that constitutes the initial distribution grid, which correspond to the upper left, upper right, lower left, and lower right corners of the initial distribution grid, respectively.

[0126] Among them, the baseline grid meteorological data refers to the grid meteorological data at the four corners of the grid, including the cumulative rainfall, total cloud cover and surface shortwave radiation value at the four corners of the grid.

[0127] The corner coordinates refer to the planar geographic coordinates (latitude and longitude or planar projection coordinates) corresponding to the four corners of the grid.

[0128] The relative coordinate value refers to the local normalized coordinate value of the distribution grid within the initial distribution grid, which is used to quantify the spatial offset of the distribution grid within the initial distribution grid.

[0129] For example, the server determines the initial distribution grid corresponding to the low-voltage distribution network based on the geographical area covered by the low-voltage distribution network; the grid size of the initial distribution grid is larger than a preset size; then, it obtains the reference grid meteorological data and corner coordinate values ​​corresponding to the four corners of the initial distribution grid from the grid database; then, it determines the relative coordinate values ​​of the distribution grid in the initial distribution grid based on the corner coordinate values ​​of the four corners of the distribution grid; then, it performs bilinear interpolation on the reference grid meteorological data based on the corner coordinate values ​​and the relative coordinate values ​​to obtain the grid meteorological data of the distribution grid.

[0130] In this embodiment, by using a larger initial distribution network grid as the basic data source, the reference grid meteorological data is stored only at the four corners of the initial grid, reducing the data storage volume and acquisition cost of the original meteorological data. Then, by performing bilinear interpolation to solve the grid meteorological data of the distribution network, it is beneficial to improve the spatial resolution accuracy and overall computational efficiency of distribution network risk assessment.

[0131] For example, see reference. Figure 2 First, a static ledger of the historical flood control threshold and the conversion coefficient of distributed photovoltaic power generation at the distribution network substations is constructed. Then, the rolling radar matrix for the next 1 hour and the long-term layer data in the large model are retrieved. Subsequently, the spatial bilinear interpolation resampling technology is used to stitch the coarse grid multi-layer onto a unified 1km×1km virtual microgrid. Then, the water-solar dual-channel vulnerability inference operator without tidal current physical parameters is started to run in parallel. The operator is divided into two parallel calculation channels. Channel 1 is the substation waterlogging index, which is calculated using formula (1). Channel 2 is the photovoltaic radiation attenuation chain, which is calculated using formula (2). After the dual-channel calculation is completed, the dual-channel temporal vulnerability index is aggregated and entered into the decision-making layer scanning engine. The decision-making layer dynamically scans the microgrid g and judges whether it simultaneously meets two conditions: waterlogging. If the index is ≡0 and the photovoltaic radiation attenuation deviation is <10%, and the judgment result is yes, it means that the microgrid has no meteorological over-limit risk. Then, feature space pruning and hiding, complete removal of the rendering queue and release of core computing load are performed. If the judgment result is no, it means that the microgrid has a high risk of meteorological over-limit. Then, the remaining high-risk microgrids are extracted, and integer step discretization and quantization are performed on continuous feature values. After the two branches are processed, the unified emergency front-end GIS system is called to perform highlight coloring mapping of the microgrid key asset spatial topology map. Then, the nonlinear power flow equation of the power grid is completely decoupled, and the dimensionless low-voltage distribution network comprehensive source-load imbalance risk warning signal of level 1-4 is directly output. Finally, the emergency linkage control response is triggered to guide the pre-deployment of mobile water pumps and the active adjustment of the microgrid cluster energy storage depth.

[0132] In one exemplary embodiment, such as Figure 3 As shown, another method for microgrid risk mapping of critical assets in distribution networks is provided. Taking the application of this method to servers as an example, the specific steps include:

[0133] Step S301: Obtain the grid meteorological data of the distribution grid of the low-voltage distribution network, as well as the first asset data of the substation assets and the second asset data of the photovoltaic power station assets in the distribution grid; the grid meteorological data shall include at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid shall be smaller than the preset size.

[0134] Step S302: Extract the critical rainfall threshold of the substation assets from the first asset data.

[0135] Step S303: If the cumulative rainfall is less than or equal to the critical rainfall threshold, determine the waterlogging index of the substation asset as the preset waterlogging index; if the cumulative rainfall is greater than the critical rainfall threshold, determine the waterlogging index of the substation asset based on the cumulative rainfall and the critical rainfall threshold.

[0136] Step S304: Extract the irradiance conversion coefficient of the photovoltaic power station assets from the second asset data.

[0137] Step S305: Determine the initial irradiance value of the photovoltaic power station assets based on the total cloud cover, surface shortwave radiation value, and irradiance conversion coefficient.

[0138] Step S306: Adjust the initial irradiance value based on the cumulative rainfall to obtain the effective irradiance value of the photovoltaic power station asset.

[0139] Step S307: Determine the output degradation rate of the photovoltaic power station assets based on the effective irradiance value.

[0140] Step S308: From each distribution network grid, determine the redundant distribution network grids whose waterlogging index is equal to the preset waterlogging index and whose power output attenuation rate is less than the preset power output attenuation rate.

[0141] Step S309: Delete redundant distribution network grids from the distribution network grid to obtain the target distribution network grid that meets the preset conditions.

[0142] Step S310: Determine the first risk value of the target distribution network grid based on the waterlogging index of the substation assets in the target distribution network grid, and determine the second risk value of the target distribution network grid based on the power output attenuation rate of the photovoltaic power station assets in the target distribution network grid.

[0143] Step S311: The first risk value and the second risk value are fused to obtain the fused risk value of the target distribution network grid.

[0144] Step S312: Determine the grid risk level of the target distribution network grid based on the fusion risk value.

[0145] Step S313: Generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0146] In the aforementioned microgrid risk mapping method for key assets of the distribution network, when identifying risks in the low-voltage distribution network, it acquires grid meteorological data containing cumulative rainfall, total cloud cover, and surface shortwave radiation values ​​under a small-sized distribution network grid, as well as substation primary asset data and photovoltaic power station secondary asset data. Based on the cumulative rainfall combined with substation asset data, it calculates the substation waterlogging index, and then integrates the cumulative rainfall, total cloud cover, surface shortwave radiation, and photovoltaic asset data to solve for the effective photovoltaic irradiance value and further derive the photovoltaic power output attenuation rate. It simultaneously quantifies the two types of related disaster indicators of substation waterlogging and photovoltaic power output attenuation, overcoming the shortcomings of the traditional single-factor judgment mode that cannot couple the synergistic effects of the two types of disasters. It then combines the two indicators to screen target distribution network grids and match the corresponding grid risk levels to generate an overall risk mapping result, comprehensively taking into account the synergistic disaster effects of waterlogging and photovoltaic power output attenuation, thereby eliminating the risk identification bias caused by single-factor judgment and improving the risk identification accuracy of the low-voltage distribution network.

[0147] In one exemplary embodiment, to more clearly illustrate the risk mapping method for microgrids of critical distribution network assets provided in this application, the following specific embodiment will be used to describe the method in detail. In one embodiment, this application also provides another risk mapping method for microgrids of critical distribution network assets. Specifically, it includes the following:

[0148] This embodiment proposes a microgrid risk mapping method for key assets in power distribution networks based on high-resolution radar short-term extrapolation. Its core process strictly follows a progressive sequence, including digital alignment of asset ledgers, temporal extrapolation of vulnerability in both water and optical channels, pruning of spatial features of risk-free assets, and dimensionless risk map mapping. The specific steps are as follows:

[0149] Step 1: Data entry and multi-layer spatiotemporal alignment process for key assets in the power distribution network.

[0150] This step aims to digitally align the scattered, widely distributed low-voltage distribution network assets with multi-source, multi-scale weather physical fields on a unified microscopic spatiotemporal platform. Specific technological methods are as follows:

[0151] 1. Construct a static ledger of the geospatial coordinates of power distribution network assets:

[0152] Through the Power Management System (PMS), the point-like core assets of 220kV and below distribution networks and microgrid clusters across the province / city are extracted and fully entered.

[0153] Targeting the assets of various 110kV / 35kV urban low-lying substations The precise GPS geospatial coordinates were entered, and its flood control design elevation was compared with historical waterlogging damage records. The historical critical rainfall tolerance threshold for flood control was determined by referring to a table. (Unit: millimeters).

[0154] For each distributed photovoltaic power station asset (Including rooftop distributed photovoltaic and microgrid-side centralized photovoltaic), enter its precise GPS geospatial coordinates, inverter rated capacity, and static standard irradiance conversion factor. .

[0155] 2. Synchronously retrieve multi-source heterogeneous dynamic meteorological layer data streams:

[0156] Through a high-speed meteorological data line, the rolling vertically integrated liquid water (VIL) image matrix generated in real time by a self-developed refined short-term radar extrapolation network model is retrieved for the next hour (updated every 6 minutes, for a total of 12 consecutive frames). .

[0157] Synchronous and asynchronous calls are made to the large-scale model base for medium- and long-term spatiotemporal numerical forecasting to extract implicit feature variable layers covering the target area for the next 1-3 days, specifically including: the total cloud cover matrix. and surface shortwave radiation matrix .

[0158] 3. Spatial resampling and multi-layer digital stitching:

[0159] Since the total cloud cover and surface shortwave radiation variables output by the large model are at a coarse-grid spatial resolution of 0.25 degrees, this embodiment utilizes the spatial bilinear interpolation operator to uniformly resample and sparsely project the coarse-grid dynamic feature layer of the large model onto a 1km×1km virtual spatial digital microgrid consistent with the self-developed short-range radar. superior.

[0160] Subsequently, the substation coordinates and photovoltaic power station coordinates Dynamic retrieval mapped to the corresponding microgrid and In this process, the spatiotemporal overlay of multiple layers, including "assets, short-term rainfall, macroscopic cloud variables, and surface radiation," is completed within a 100-meter-level geographic raster grid.

[0161] It should be noted that this solution incorporates a refined short-term radar extrapolation network with a high-fidelity pixel-accurate spatiotemporal alignment operator. Its basic data processing architecture is as follows: The input data of this network consists of radar base data from multiple consecutive historical time steps, and its data dimension can be represented as a high-dimensional tensor structure. (Where B is the batch size, T is the number of historical time steps, C is the number of feature channels, and H and W are the spatial aspect ratio and resolution). Its output is the reflectance prediction tensor for the next preset time step.

[0162] Furthermore, during the projection from the coarse mesh to the micro mesh, the spatiotemporal operator achieves precise coordinate system alignment based on the principle of spatial bilinear interpolation. Specifically, for any center coordinate in the target micro mesh, the algorithm addresses the four nearest pixel nodes in the coarse mesh feature map and performs weighted allocation and weighted summation based on the reciprocal of the distance. This mathematical transformation path ensures that the geometry and edge features of the radar echo are not distorted during cross-scale feature mapping, thereby achieving high-fidelity alignment of interface parameters.

[0163] Step 2: Deduction process for asset meteorological uncertainty based on dual-channel water and light.

[0164] This step uses a dual-channel water-optical vulnerability extrapolation operator that operates in parallel to directly calculate the personalized over-limit impacts of meteorological field evolution on heterogeneous distribution network assets, thereby completely eliminating the dependence on traditional electrical power flow nonlinear equations that consume high computing power.

[0165] 1. Construct a mathematical model for the weather vulnerability of assets in a dual-channel system:

[0166] Within the aligned, unified digital microgrid, targeting substation asset points and photovoltaic power station assets Two independent Standalone mathematical equations are started to perform time-series evolution deduction, as shown in equation (1) and equation (2).

[0167] 2. Explanation of physical variables and coefficients in the formula:

[0168] Substation Waterlogging Vulnerability Evolution Index. This index indicates the vulnerability of substations to waterlogging within a given timeframe. At that time, the first The logarithmic index of the real-time risk of urban flooding at a low-lying substation in City No. 1 due to excessive cumulative rainfall.

[0169] Radar-to-Rainfall Physical Conversion Coefficient. A scaling factor used to convert the radar VIL reflectivity characteristic matrix into minute-level instantaneous surface rainfall intensity with high fidelity.

[0170] Asset Physical Micro-grid Coordinates. Representing substations. and distributed photovoltaic power stations After spatial interpolation, the precise physical coordinates of the 1km×1km static digital microgrid layer are obtained.

[0171] Photovoltaic Available Irradiance Estimation Time-series Chain. This indicates the time series for estimating available photovoltaic irradiance over a prediction lead time of [missing information]. At that time, the first Due to the combined effects of instantaneous cloud cover at high altitudes and absorption and scattering by near-surface precipitation particles, the actual effective total solar radiation energy that the No. 1 distributed photovoltaic power station can receive is limited.

[0172] Clear-sky surface short-wave radiation downwards matrix. Output from numerical weather prediction base, aligned to a microgrid. The theoretical maximum surface shortwave radiation energy density at that location.

[0173] Total Cloud Cover Coefficient. (This refers to a coefficient related to cloud cover.) Intervals are used to characterize microgrids. The percentage of total cloud cover in the sky.

[0174] Raindrop Scattering Non-linear Attenuation Penalty Constant: This is an a priori mathematical constant used to quantitatively characterize the refraction, scattering, and non-linear attenuation effects of raindrop particles of different densities near the ground on incident solar photovoltaic radiation during strong convection.

[0175] 3. Explanation of the mathematical control logic for dual-channel derivation:

[0176] Channel 1 control logic: The system extrapolates the radar short-term image sequence along the time axis. Continuous integral calculations are performed to dynamically accumulate and predict rainfall. When the accumulated rainfall is less than or equal to the substation's own flood control tolerance threshold... When the rainfall intensity is exceeded, the formula outputs a value of 0, indicating that the substation is fully resistant to the rainfall intensity. Once the accumulated rainfall exceeds the limit, the formula outputs a rapidly increasing positive vulnerability value through a logarithmic nonlinear mapping, thus achieving a flexible measurement of the depth of waterlogging evolution.

[0177] Channel 2 control logic: The system uses cascading items The attenuation caused by macroscopic cloud cover is removed, and then a nonlinear penalty term is applied. By subtracting the scattering loss from local rainfall near the ground captured by short-range radar, the characteristic flow of "source-side impact" caused by a sudden drop in photovoltaic power under extreme weather conditions can be deduced with great robustness.

[0178] Step 3: Spatial pruning process for disaster-free asset grid features.

[0179] Because the number of equipment ledgers and inverter nodes on the low-voltage distribution network side typically increases dramatically (tens of thousands to hundreds of thousands across a province or city), full tracking and real-time online rendering would cause a flood of alarms in the power grid dispatch center's backend, resulting in a severe reduction in computational efficiency. This step introduces a bidirectional safety threshold pruning operator to filter out non-hazardous assets, greatly reducing the computational load on the backend.

[0180] 1. Two-way safety threshold scanning micro-operation:

[0181] After completing the dual-channel vulnerability index calculation in step 2, the algorithm module performs a dynamic high-frequency scan of the entire asset microgrid at the decision level. This applies to any microgrid. Set the following two-way security decision thresholds:

[0182] Threshold A (No Exceeding Limit for Flooding): The flood vulnerability evolution index of all substations associated within this grid is always equal to zero, i.e. .

[0183] Threshold B (Low PV Fluctuation): The deviation of the available irradiance of distributed PV within this grid is extremely low, i.e., its real-time calculated value. Compared with theoretical clear sky irradiance The attenuation deviation ratio between them is less than 10%.

[0184] 2. Feature space pruning and hiding:

[0185] If a microgrid of an asset simultaneously meets both threshold A and threshold B, it is determined that the microgrid asset has no risk of exceeding meteorological limits within the current forecast window. The decision-making algorithm module immediately performs feature space pruning and hiding on the grid, completely removing it from the core high-risk assessment matrix and preventing it from allocating computational memory to the subsequent GIS map rendering engine. Through this pruning micro-operation, more than 85% of risk-free redundant grids across the province can be eliminated, significantly improving the overall computational energy efficiency of the edge host.

[0186] Step 4: Unify the microgrid asset risk map mapping and joint decision-making process.

[0187] This step involves discretizing and quantizing the microgrids of risky critical assets that were filtered and retained in step 3, and generating the final low-voltage distribution network integrated source-load imbalance control interface.

[0188] 1. Stepped discretization and spatial topological coloring mapping:

[0189] High-risk distribution network asset microgrids that were not hidden by pruning were extracted, and their continuous dual-channel vulnerability feature values ​​were discretized using integer stepwise methods. The multi-dimensional map layer of the Geographic Information System (GIS) of the unified emergency front-end of the power grid was directly called. Based on the risk integer level, the substation icons and photovoltaic power plant microgrid areas were subjected to high-brightness explicit color-map spatial coloring mapping (Risk Atlas Mapping) to achieve a panoramic visualization of the disaster area.

[0190] 2. Integrated source-load imbalance early warning output without power flow parameters:

[0191] The decision-making algorithm completely bypasses the extremely complex multi-objective nonlinear balance equations of node power flow within the distributed distribution network, directly applying the derived photovoltaic radiation attenuation chain. and substation waterlogging index The package uses a standard data service interface to send out dimensionless low-voltage distribution network integrated source-load imbalance risk warning signals (levels 1-4) in real time.

[0192] Output early warning action instructions: The early warning signal directly drives the distribution network emergency control front end to execute one-click disaster prevention and emergency decision-making: For high-risk grids with flooding in substations, a mobile water pump team can be dispatched in advance to the designated GPS coordinate asset point with one click; For high-risk grids with large-area power drop in photovoltaics, the local energy storage equipment within the local microgrid cluster can be adjusted to adjust the charging and discharging depth in advance, and the automatic backup and self-transfer system can be locked in advance, and a low-voltage distribution network active disconnection independent operation plan can be prepared, thereby achieving proactive closed-loop defense against risks.

[0193] The decision-making level constructed a set of four-state transition spatiotemporal state machine mapping rules: when When the threshold is reached, output level 1 (normal attention state); when it exceeds... And if the flood control limit is not reached, output Level 2 (situational awareness state, alarm only, no action); when any channel exceeds the limit, triggering... When the output reaches level 3 (emergency pre-state, one-click assignment of water pump); when both channels trigger extreme values ​​simultaneously... At that time, the output is at level 4 (restore alarm cancellation / network switching state, active interlocking and automatic transfer). Through this state machine rule, a rigorous mapping from continuous meteorological characteristics to discrete control commands is achieved.

[0194] For example, see reference. Figure 4The diagram shows a comprehensive disaster prevention control architecture for distribution network assets based on microgrid multi-layer overlay. Internally, the architecture consists of four layers from top to bottom. The first layer is the data layer, responsible for inputting heterogeneous meteorological fields and recording static asset ledgers. The data layer outputs information to the second layer, the model layer. The model layer performs 1km short-range radar extrapolation and large-scale multi-radiative variable matrix calculations. The model layer's output data is transmitted to the third layer, the decision layer, to complete spatiotemporal multi-layer stitching and dynamic feedback verification. Simultaneously, it is mapped through a link labeled as spatial bilinear interpolation resampling to the multi-scale meteorological multi-layer gridded seamless stitching mechanism within the three major inventions' core mapping mechanism. The decision layer also relies on the microgrid spatiotemporal overlay layer lookup verification loop to feed back verification data to the model layer. The decision layer's output is then processed through links labeled as flood prevention lookup and photovoltaic attenuation chain. The data transmitted to the dual-channel water-solar parameter-free vulnerability extrapolation model in the three major invention points hard core mapping mechanism is ultimately sent to the fourth layer, the application layer. The application layer is a low-voltage distribution network unified emergency front-end system without power flow parameters. The application layer generates a dimensionless comprehensive source-load imbalance early warning signal and outputs it outward. In addition to the aforementioned invention points, the three major invention points hard core mapping mechanism also includes low-voltage grid asset feature space pruning and risk map coloring. The calculation results of the three major invention points are looped back to the top-level distribution network asset disaster prevention full-process control architecture based on microgrid multi-layer overlay. This provides underlying algorithm support for the data layer, model layer, decision layer, and application layer, forming a complete distribution network asset disaster prevention full-process control system with multi-level data flow, dynamic closed-loop verification, and support from the three core invention algorithms.

[0195] In the above embodiments, when identifying risks in low-voltage distribution networks, grid meteorological data including cumulative rainfall, total cloud cover, and surface shortwave radiation values ​​are acquired from small-sized distribution network grids, along with substation first asset data and photovoltaic (PV) station second asset data. The substation flooding index is calculated based on cumulative rainfall combined with substation asset data. Then, the effective irradiance value of PV is solved by integrating cumulative rainfall, total cloud cover, surface shortwave radiation, and PV asset data, further deriving the PV output attenuation rate. Simultaneously, the two related disaster indicators of substation flooding and PV output attenuation are quantified. This overcomes the deficiency of traditional single-factor judgment models that cannot couple the synergistic effects of two types of disasters. Furthermore, the two indicators are combined to screen target distribution network grids and match the corresponding grid risk levels to generate an overall risk mapping result. This comprehensively considers the synergistic disaster effects of flooding and PV output attenuation, thereby eliminating the risk identification bias caused by single-factor judgment and improving the accuracy of low-voltage distribution network risk identification. Moreover, under extreme weather conditions, the water-solar-electricity multi-hazard chain is highly coupled. If traditional physical power flow equations are used for microgrid scheduling, it is prone to parameter explosion and non-convergence problems. This solution not only achieves deep physical-level decoupling of meteorological characteristics and highly dynamic electrical parameters, but also effectively solves the engineering bottleneck of insufficient edge computing power under extreme disasters by pruning 85% of the mesh features, achieving millisecond-level response.

[0196] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0197] Based on the same inventive concept, this application also provides a distribution network critical asset microgrid risk mapping device for implementing the above-mentioned distribution network critical asset microgrid risk mapping method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more distribution network critical asset microgrid risk mapping device embodiments provided below can be found in the limitations of the distribution network critical asset microgrid risk mapping method above, and will not be repeated here.

[0198] In one exemplary embodiment, such as Figure 5As shown, a microgrid risk mapping device for key assets in a distribution network is provided, comprising: a data acquisition module 501, a data determination module 502, an attenuation rate determination module 503, a grid determination module 504, and a result generation module 505, wherein:

[0199] The data acquisition module 501 is used to acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as the first asset data of substation assets and the second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than the preset size.

[0200] The data determination module 502 is used to determine the waterlogging index of the substation assets based on the cumulative rainfall and the first asset data, and to determine the effective irradiance value of the photovoltaic power station assets based on the cumulative rainfall, total cloud cover, surface shortwave radiation value and the second asset data.

[0201] The attenuation rate determination module 503 is used to determine the output attenuation rate of photovoltaic power station assets based on the effective irradiance value.

[0202] The grid determination module 504 is used to determine the target distribution grid that meets the preset conditions from each distribution grid based on the waterlogging index and the power output attenuation rate.

[0203] The result generation module 505 is used to obtain the grid risk level of the target distribution network grid and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

[0204] In an exemplary embodiment, the grid determination module 504 is further configured to determine, from each distribution grid, a redundant distribution grid whose waterlogging index is equal to a preset waterlogging index and whose power output attenuation rate is less than a preset power output attenuation rate; delete the redundant distribution grid from the distribution grid to obtain a target distribution grid that meets the preset conditions.

[0205] In an exemplary embodiment, the result generation module 505 is further configured to determine a first risk value of the target distribution network grid based on the waterlogging index of the substation assets in the target distribution network grid, and a second risk value of the target distribution network grid based on the output attenuation rate of the photovoltaic power station assets in the target distribution network grid; to perform fusion processing on the first risk value and the second risk value to obtain a fused risk value of the target distribution network grid; and to determine the grid risk level of the target distribution network grid based on the fused risk value.

[0206] In an exemplary embodiment, the data determination module 502 is further configured to extract the critical rainfall threshold of the substation asset from the first asset data; if the cumulative rainfall is less than or equal to the critical rainfall threshold, determine the waterlogging index of the substation asset as a preset waterlogging index; if the cumulative rainfall is greater than the critical rainfall threshold, determine the waterlogging index of the substation asset based on the cumulative rainfall and the critical rainfall threshold.

[0207] In an exemplary embodiment, the data determination module 502 is further configured to extract the irradiance conversion coefficient of the photovoltaic power station asset from the second asset data; determine the initial irradiance value of the photovoltaic power station asset based on the total cloud cover, surface shortwave radiation value and irradiance conversion coefficient; and adjust the initial irradiance value based on the cumulative rainfall to obtain the effective irradiance value of the photovoltaic power station asset.

[0208] In an exemplary embodiment, the data acquisition module 501 is further configured to determine the initial distribution grid corresponding to the low-voltage distribution network; the grid size of the initial distribution grid is larger than a preset size; acquire the reference grid meteorological data and corner coordinate values ​​corresponding to the four corners of the initial distribution grid; acquire the relative coordinate values ​​of the distribution grid in the initial distribution grid; and perform bilinear interpolation on the reference grid meteorological data based on the corner coordinate values ​​and the relative coordinate values ​​to obtain the grid meteorological data of the distribution grid.

[0209] Each module in the aforementioned microgrid risk mapping device for critical distribution network assets can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0210] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database stores data such as cumulative rainfall and total cloud cover. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a microgrid risk mapping method for critical assets in a power distribution network.

[0211] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0212] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0213] In one exemplary embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above-described method embodiments.

[0214] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0215] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0216] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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, they should be considered to be within the scope of this specification.

[0217] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A microgrid risk mapping method for key assets in a power distribution network, characterized in that, The method includes: Acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as first asset data of substation assets and second asset data of photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size; Based on the cumulative rainfall and the first asset data, the waterlogging index of the substation asset is determined, and based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data, the effective irradiance value of the photovoltaic power station asset is determined. Based on the effective irradiance value, the output attenuation rate of the photovoltaic power station asset is determined; Based on the waterlogging index and the power output attenuation rate, target distribution grids that meet preset conditions are determined from each of the distribution grids; Obtain the grid risk level of the target distribution network grid, and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

2. The method according to claim 1, characterized in that, The step of determining the target distribution network grid that meets the preset conditions from each of the distribution network grids based on the waterlogging index and the power output attenuation rate includes: From each of the distribution network grids, a redundant distribution network grid is identified where the waterlogging index is equal to the preset waterlogging index and the power output attenuation rate is less than the preset power output attenuation rate. The redundant distribution network grid is deleted from the distribution network grid to obtain the target distribution network grid that meets the preset conditions.

3. The method according to claim 2, characterized in that, The process of obtaining the grid risk level of the target distribution network grid includes: Based on the waterlogging index of the substation assets in the target distribution network grid, the first risk value of the target distribution network grid is determined, and based on the power output attenuation rate of the photovoltaic power station assets in the target distribution network grid, the second risk value of the target distribution network grid is determined. The first risk value and the second risk value are fused together to obtain the fused risk value of the target distribution network grid; Based on the fusion risk value, the grid risk level of the target distribution network grid is determined.

4. The method according to claim 1, characterized in that, The step of determining the waterlogging index of the substation asset based on the cumulative rainfall and the first asset data includes: From the first asset data, the critical rainfall threshold of the substation asset is extracted; If the cumulative rainfall is less than or equal to the critical rainfall threshold, the waterlogging index of the substation asset is determined to be the preset waterlogging index; If the cumulative rainfall exceeds the critical rainfall threshold, the flooding index of the substation asset is determined based on the cumulative rainfall and the critical rainfall threshold.

5. The method according to claim 1, characterized in that, The determination of the effective irradiance value of the photovoltaic power station asset based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value, and the second asset data includes: The irradiance conversion coefficient of the photovoltaic power station asset is extracted from the second asset data; The initial irradiance of the photovoltaic power station asset is determined based on the total cloud cover, the surface shortwave radiation value, and the irradiance conversion coefficient. Based on the cumulative rainfall, the initial irradiance value is adjusted to obtain the effective irradiance value of the photovoltaic power station asset.

6. The method according to any one of claims 1 to 5, characterized in that, The acquisition of grid meteorological data of the low-voltage distribution network includes: The initial distribution grid corresponding to the low-voltage distribution network is determined; the grid size of the initial distribution grid is larger than the preset size; Obtain the meteorological data and corner coordinates of the reference grid corresponding to the four corners of the initial distribution network grid; Obtain the relative coordinates of the distribution network grid in the initial distribution network grid, and perform bilinear interpolation on the reference grid meteorological data based on the corner coordinates and the relative coordinates to obtain the grid meteorological data of the distribution network grid.

7. A microgrid risk mapping device for key assets in a power distribution network, characterized in that, The device includes: The data acquisition module is used to acquire grid meteorological data of the distribution grid of the low-voltage distribution network, as well as the first asset data of the substation assets and the second asset data of the photovoltaic power station assets in the distribution grid; the grid meteorological data includes at least the cumulative rainfall, total cloud cover and surface shortwave radiation value of the distribution grid; the grid size of the distribution grid is smaller than a preset size; The data determination module is used to determine the waterlogging index of the substation asset based on the cumulative rainfall and the first asset data, and to determine the effective irradiance value of the photovoltaic power station asset based on the cumulative rainfall, the total cloud cover, the surface shortwave radiation value and the second asset data. The attenuation rate determination module is used to determine the output attenuation rate of the photovoltaic power station asset based on the effective irradiance value. The grid determination module is used to determine the target distribution grid that meets the preset conditions from each of the distribution grids based on the waterlogging index and the power output attenuation rate. The result generation module is used to obtain the grid risk level of the target distribution network grid and generate the risk mapping result of the low-voltage distribution network based on the grid risk level.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

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

Images