A new energy station extreme weather precursor identification and early warning method and system based on a meteorological disaster propagation network, and a storage medium

Abstract

The application discloses a new energy station extreme weather precursor identification and early warning method and system based on a meteorological disaster propagation network, relates to the technical field of new energy station meteorological monitoring and safety prevention and control, and comprises the following steps: acquiring spatial geographic data, historical meteorological data and real-time meteorological data of a new energy station; constructing a meteorological disaster propagation network; calculating the disaster propagation probability between each grid node; identifying a precursor node in the grid node and calculating a current meteorological disaster risk value; taking the precursor node as a disaster source node, predicting the propagation path, predicted arrival time and influence range of the disaster source node to the new energy station; and determining an extreme weather early warning result and corresponding prevention and control measure strategy according to the current meteorological disaster risk value, propagation path, predicted arrival time and influence range. The application can improve the timeliness and accuracy of new energy station extreme weather precursor identification and early warning.

Description

Technical Field

[0001] This application relates to the field of meteorological monitoring and safety control technology for new energy power stations, and in particular to a method, system, and storage medium for identifying and issuing early warnings of extreme weather precursors for new energy power stations based on a meteorological disaster propagation network. Background Technology

[0002] The power generation efficiency, equipment safety, and grid connection stability of renewable energy power plants are all closely related to meteorological conditions, and they are particularly susceptible to extreme weather events such as typhoons, cold waves, severe convection, localized short-term strong winds, and heavy rainfall. Current meteorological early warning systems for renewable energy power plants mainly rely on meteorological station data, low spatial resolution grid forecasts, or single-point station monitoring results. These systems struggle to reflect the complex terrain surrounding the power plant, underlying surface differences, and microscale atmospheric changes, leading to delayed identification of extreme weather precursors and hindering timely early warning. Furthermore, existing risk assessment methods often use single static thresholds to determine meteorological indicators for warning purposes, typically focusing only on the instantaneous state of a single measuring point. They lack a characterization of how disasters form, spread, and diffuse spatially, and also lack predictions of the impact range and arrival time. This results in low accuracy in dynamic identification and early warning of extreme weather precursors, making it difficult to directly support power forecasting adjustments, energy storage scheduling optimization, and equipment zoning protection.

[0003] Therefore, improving the timeliness and accuracy of identifying and issuing early warnings of extreme weather precursors at new energy power plants has become a pressing technical problem that needs to be solved in this field. Summary of the Invention

[0004] The purpose of this application is to provide a method, system, and storage medium for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks, which can improve the timeliness and accuracy of identifying and issuing early warnings of extreme weather precursors at new energy power stations.

[0005] To achieve the above objectives, this application provides the following solution.

[0006] In the first aspect, this application provides a method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks, including the following steps.

[0007] Acquire spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations.

[0008] Based on the aforementioned spatial geographic data, a meteorological disaster propagation network is constructed. The meteorological disaster propagation network is obtained by dividing the area surrounding the new energy power station into spatial grids, with the new energy power station as the center. Each spatial grid in the meteorological disaster propagation network is defined as a grid node.

[0009] Based on the historical meteorological data, the probability of disaster propagation between each grid node is calculated; the probability of disaster propagation is used to characterize the propagation relationship of extreme weather disasters between different grid nodes.

[0010] Based on the real-time meteorological data and the historical meteorological data, precursor nodes in the grid nodes are identified, and the current meteorological disaster risk value of the precursor nodes is calculated.

[0011] Using the precursor node as the disaster source node, and based on the meteorological disaster propagation network and the disaster propagation probability, the propagation path, expected arrival time, and impact range of the disaster source node to the new energy power station are predicted.

[0012] Based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the impact range, the extreme weather warning results and corresponding prevention and control measures and strategies are determined.

[0013] Secondly, this application provides a new energy power station extreme weather precursor identification and early warning system based on a meteorological disaster propagation network, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the new energy power station extreme weather precursor identification and early warning method based on a meteorological disaster propagation network.

[0014] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network.

[0015] According to the specific embodiments provided in this application, this application has the following technical effects.

[0016] This application provides a method, system, and storage medium for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network. By constructing a meteorological disaster propagation network centered on the new energy power station, the propagation relationship of extreme weather disasters between spatial grid nodes can be clearly characterized, enhancing the ability to depict disaster propagation patterns. Calculating the disaster propagation probability between grid nodes based on historical meteorological data provides reliable data support for predicting the propagation path, expected arrival time, and impact range of extreme weather. Combining real-time and historical meteorological data to identify precursor nodes and calculate the current meteorological disaster risk value allows for the early capture of extreme weather precursor signals, improving the timeliness and accuracy of precursor identification, thereby enhancing the timeliness and accuracy of extreme weather precursor identification and early warning at new energy power stations. Predicting the propagation path, arrival time, and impact range using precursor nodes as disaster source nodes enables accurate prediction of the extreme weather impact process, providing a quantitative basis for early warning decisions. Determining the early warning results and control measures based on the disaster risk value, propagation path, arrival time, and impact range improves the targeting of early warnings and the effectiveness of control measures, ensuring the safe and stable operation of new energy power stations. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 An application environment diagram of an extreme weather precursor identification and early warning method for new energy power stations based on a meteorological disaster propagation network, provided as an embodiment of this application; Figure 2 A flowchart illustrating an embodiment of this application provides a method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network; Figure 3 A schematic diagram of the structure of an extreme weather precursor identification and early warning system for new energy power stations based on a meteorological disaster propagation network, provided as an embodiment of this application; Figure 4 This is a schematic diagram of another extreme weather precursor identification and early warning system for new energy power stations based on a meteorological disaster propagation network, provided as an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides a method, system, and storage medium for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network. By constructing a meteorological disaster propagation network, it achieves accurate prediction of disaster propagation paths, arrival times, and impact ranges; by using multi-altitude meteorological monitoring and precursor identification, it improves the timeliness and accuracy of capturing extreme weather precursors; by linking multi-level early warnings with graded prevention and control, it achieves efficient conversion of early warning information into station operation control and equipment protection; and by using a feedback mechanism to dynamically optimize model parameters, it improves the system's long-term adaptive capability and early warning accuracy.

[0021] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0022] The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on other servers. Terminal 102 can send spatial geographic data, historical meteorological data, and real-time meteorological data of the new energy power station to server 104. After receiving the spatial geographic data, historical meteorological data, and real-time meteorological data of the new energy power station, server 104 constructs a meteorological disaster propagation network based on the spatial geographic data; calculates the disaster propagation probability between each grid node based on the historical meteorological data; identifies precursor nodes in the grid nodes based on the real-time meteorological data and historical meteorological data, and calculates the current meteorological disaster risk value; uses precursor nodes as disaster source nodes, predicts the propagation path, expected arrival time, and impact range of the disaster source nodes to the new energy power station; and determines the extreme weather warning results and corresponding prevention and control strategies based on the current meteorological disaster risk value, propagation path, expected arrival time, and impact range. Server 104 can feed back the obtained video tags for the video to terminal 102. Furthermore, in some embodiments, the method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly perform extreme weather precursor identification and early warning processing on the spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations. Alternatively, the server 104 can obtain the spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations from the data storage system and perform extreme weather precursor identification and early warning processing on the spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations.

[0023] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, and IoT devices. The server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers, or it can be a cloud server.

[0024] In one exemplary embodiment, such as Figure 2 As shown, a method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the following steps are included.

[0025] Step 1: Obtain spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations.

[0026] Step 2: Based on the spatial geographic data, construct a meteorological disaster propagation network; the meteorological disaster propagation network is obtained by dividing the area around the new energy power station into spatial grids with the new energy power station as the center, and each spatial grid in the meteorological disaster propagation network is defined as a grid node.

[0027] Step 3: Based on the historical meteorological data, calculate the disaster propagation probability between each grid node; the disaster propagation probability is used to characterize the propagation relationship of extreme weather disasters between different grid nodes.

[0028] Step 4: Based on the real-time meteorological data and the historical meteorological data, identify the precursor nodes in the grid nodes and calculate the current meteorological disaster risk value of the precursor nodes.

[0029] Step 5: Using the precursor node as the disaster source node, predict the propagation path, estimated arrival time and impact range of the disaster source node to the new energy power station based on the meteorological disaster propagation network and the disaster propagation probability.

[0030] Step 6: Based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the impact range, determine the extreme weather warning results and corresponding prevention and control measures and strategies.

[0031] Implementing steps 1 to 6 above enables the construction of a meteorological disaster propagation network based on a spatial grid, accurately depicting the propagation relationship of extreme weather around the power station, effectively identifying precursor nodes and calculating disaster risks by combining real-time and historical meteorological data, accurately predicting the path, estimated arrival time, and impact range of disasters propagating to new energy power stations, generating reliable early warning results and matching corresponding prevention and control strategies, thereby achieving early perception, accurate prediction, and effective prevention and control of extreme weather at new energy power stations, and improving the timeliness, accuracy, and safety of extreme weather response at the power stations.

[0032] As an optional implementation, step 2 involves constructing a meteorological disaster propagation network based on the spatial geographic data, specifically including the following steps.

[0033] Based on the spatial geographic data, the area around the new energy power station is divided into several spatial grids of a predetermined size, resulting in several grid nodes that constitute the meteorological disaster propagation network.

[0034] As an optional implementation, step 4 involves identifying precursor nodes in the grid nodes based on the real-time meteorological data and the historical meteorological data, and calculating the current meteorological disaster risk value of the precursor nodes, specifically including the following steps.

[0035] Step 41: Perform outlier removal, time synchronization correction, and deviation compensation on the real-time meteorological data to obtain corrected real-time meteorological data.

[0036] Step 42: Calculate the humidity vertical gradient, wind speed shear rate, and Richardson number based on the corrected real-time meteorological data.

[0037] Step 43: Identify precursor nodes in the grid nodes based on the humidity vertical gradient, the wind speed shear rate, and the Richardson number.

[0038] Step 44: Based on the historical meteorological data of the precursor node, combined with the humidity vertical gradient, the wind speed shear rate and the Richardson number, calculate the confidence level of the precursor signal.

[0039] Step 45: Calculate the current meteorological disaster risk based on the confidence level of the precursor signals.

[0040] As an optional implementation, step 5, taking the precursor node as the disaster source node, predicts the propagation path, expected arrival time, and impact range of the disaster source node to the new energy power station based on the meteorological disaster propagation network and the disaster propagation probability, specifically including the following steps.

[0041] Step 51: Using the precursor node as the disaster source node, and based on the meteorological disaster propagation network, use the Dijkstra algorithm to search for the propagation path from the disaster source node to the grid node of the new energy power station.

[0042] Step 52: Based on the disaster propagation probability between each grid node on the propagation path and combined with the historical average propagation speed in the historical meteorological data, calculate the estimated arrival time of the disaster at the new energy power station.

[0043] Step 53: Based on the disaster propagation probability among the grid nodes, determine the set of nodes whose disaster propagation probability is greater than a preset threshold, and use the set of nodes as the impact range of the disaster on the new energy power station.

[0044] As an optional implementation, step 6 involves determining the extreme weather warning result and corresponding prevention and control measures and strategies based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the impact range. This specifically includes the following steps.

[0045] Step 61: Determine the total number of nodes in the meteorological disaster propagation network and the number of affected nodes in the affected area.

[0046] Step 62: Calculate the basic risk ratio based on the total number of nodes and the number of affected nodes.

[0047] Step 63: Based on the confidence level of the precursor signal, the basic risk ratio is weighted and corrected to obtain the comprehensive risk index.

[0048] Step 64: Classify the warning level according to the comprehensive risk index and generate extreme weather warning results; the extreme weather warning results include warning level, comprehensive risk index, confidence level of precursor signals, scope of impact, expected arrival time, and effective duration of the warning.

[0049] Step 65: Based on the extreme weather warning results, formulate corresponding prevention and control measures and strategies.

[0050] As an optional implementation, in step 64, the warning levels include ultra-low risk, low risk, medium risk, and high risk. In step 65, based on the extreme weather warning results, corresponding prevention and control strategies are formulated, specifically including the following prevention and control strategies.

[0051] (1) When the warning level is ultra-low risk, the new energy power station shall be kept in normal operation within the effective period of the warning and a reminder message shall be sent to the operation and maintenance personnel.

[0052] (2) When the warning level is low risk, the input meteorological parameters in the power prediction model are corrected according to the confidence level of the precursor signal and the range of influence, and the power prediction results are updated within the effective duration of the warning; the power prediction model is a mapping model used to predict the power generation of the new energy power station based on the meteorological parameters.

[0053] (3) When the warning level is medium risk, the charging and discharging strategy of the energy storage system of the new energy power station shall be adjusted according to the comprehensive risk index, the scope of impact and the estimated arrival time, and emergency capacity shall be reserved before the estimated arrival time.

[0054] (4) When the warning level is high risk, determine the equipment area that needs to be protected according to the scope of the impact, and perform emergency protection operations on the equipment in the equipment area before the expected arrival time; the emergency protection operations include at least one of wind turbine feathering shutdown, photovoltaic bracket leveling or photovoltaic panel automatic shading.

[0055] As an optional implementation, after step 6, the method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks further includes the following steps.

[0056] Step 7: Dynamically adjust the network parameters of the meteorological disaster propagation network, specifically including the following steps.

[0057] Step 71: Collect the actual disaster evolution results and equipment response results after the implementation of prevention and control measures.

[0058] Step 72: Based on the actual disaster evolution results and the equipment response results, use an online learning algorithm to update the propagation coefficient in the disaster propagation probability calculation process, and combine the newly added historical extreme weather event data to optimize the disaster propagation probability model among network nodes.

[0059] Step 73: Based on the deviation between the actual disaster evolution results and the extreme weather warning results, adjust the confidence enhancement coefficient and time decay coefficient in the calculation process of the comprehensive risk index.

[0060] Step 74: Adjust the judgment threshold in the precursor node identification process according to the actual disaster evolution results; the judgment threshold includes humidity vertical gradient threshold, wind speed shear rate threshold, Richardson number threshold and duration threshold.

[0061] Step 75: Adjust the triggering conditions in the prevention and control measures strategy based on the actual disaster evolution results and the equipment response results; the triggering conditions include the warning level classification threshold and the preset time threshold.

[0062] In an exemplary embodiment, in order to illustrate the technical solution provided by the embodiments of this application in detail, a method for identifying and warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks is provided, and its specific implementation process is as follows.

[0063] S1. Obtain spatial geographic data of new energy power stations, construct a meteorological disaster propagation network, divide the area surrounding new energy power stations into multiple spatial grids, define each spatial grid as a grid node, and calculate the disaster propagation probability between grid nodes based on historical meteorological data to characterize the propagation relationship of disasters between different grid nodes.

[0064] S2. Monitor meteorological parameters of the corresponding areas of each grid node in real time, calculate the current meteorological disaster risk, and identify precursor nodes based on the meteorological parameters.

[0065] S3. Using the precursor node as the disaster source node, and combining the disaster propagation probability, predict the propagation path, estimated arrival time, and impact range of the disaster to the station.

[0066] S4. Based on the current meteorological disaster risk, the propagation path, the expected arrival time, and the scope of impact, construct a comprehensive risk index, and generate multi-level early warning signals based on the comprehensive risk index.

[0067] S5. Based on the multi-level early warning signals and the scope of impact, and in conjunction with the expected arrival time of the disaster, implement phased prevention and control measures for the operation status of new energy power plants.

[0068] S6. Adjust the parameters of the meteorological disaster transmission network dynamically based on the effectiveness of prevention and control measures and the actual evolution of the disaster.

[0069] As one feasible approach, step S1 includes the following steps.

[0070] S1.1 Taking the new energy power station as the center, the 50km×50km area including the new energy power station is divided into a regular grid of 5km×5km (including the new energy power station), and each spatial grid is defined as a grid node.

[0071] S1.2 Based on historical meteorological data of extreme weather events such as typhoons, cold waves, and severe convective weather over the past five years, calculate the values ​​of any two grid nodes. i and j Probability of disaster transmission between .

[0072] The probability of disaster transmission The calculation formula is as follows.

[0073] (1).

[0074] in, D ij For grid nodes i With grid nodes j Euclidean distance, Δ T ij For grid nodes i With grid nodes j The temperature difference between them, Δ V ij For grid nodes i With grid nodes j The difference in wind speed between them, Δ H ij For grid nodes i With grid nodes j Humidity differences between them α , β The propagation coefficient is obtained based on historical data training. It is a nonlinear propagation function based on meteorological parameters.

[0075] As one possible implementation, step S2 includes the following steps.

[0076] S2.1 Within the 5km×5km grid nodes divided in step S1, a 1km×1km high-density monitoring subgrid is further divided to form a meteorological monitoring system covering the surrounding area of ​​the new energy power station. Each subgrid is equipped with multi-parameter sensors at heights of 1.5m, 10m, 30m, and 50m above the ground.

[0077] S2.2 Collect temperature, humidity, wind speed, wind direction, air pressure and radiation intensity data every minute.

[0078] S2.3 Perform outlier removal, time synchronization correction, and sensor deviation compensation on the collected data to obtain corrected data.

[0079] S2.4 Calculate the humidity vertical gradient, wind speed shear rate, and Richardson number based on the corrected data.

[0080] Humidity vertical gradient The calculation formula is as follows.

[0081] (2).

[0082] in, H 1.5m , H 10m , H 30m , H 50m The values ​​are relative humidity values ​​measured at heights of 1.5 meters, 10 meters, 30 meters, and 50 meters above the ground, respectively, in terms of %; Δz represents the vertical distance difference between adjacent sensors, in meters; 8.5, 20, and 20 correspond to height differences of 1.5-10m, 10-30m, and 30-50m, respectively.

[0083] Wind shear rate The calculation formula is as follows.

[0084] (3).

[0085] in, V 1.5m , V 10m , V 30m , V 50m The wind speed values ​​were measured at heights of 1.5 meters, 10 meters, 30 meters, and 50 meters above the ground, respectively, and are in m / s.

[0086] The formula for calculating Richardson numbers is as follows.

[0087] (4).

[0088] in, The value represents the Richardson number, and g is the acceleration due to gravity. In this embodiment, g is taken as 9.8 m / s². 2 ; θ For potential temperature, , T Temperature, in Kelvin (K). P This refers to atmospheric pressure (unit: hPa). P 0 is the reference air pressure. R d The gas constant for dry air. c p For isobaric specific heat capacity, P 0 = 1000 hPa R d =287J(kg / K), c p ≈1004J(kg / K), R d / c p ≈0.286; Δ θ / Δ z The potential temperature vertical gradient is calculated using the same piecewise finite difference method as humidity and wind speed, and the specific formula is as follows.

[0089] (5).

[0090] in, θ 1.5m , θ 10m , θ 30m , θ 50m The temperatures were measured at heights of 1.5 meters, 10 meters, 30 meters, and 50 meters above the ground, respectively, and are expressed in Kelvin (K).

[0091] S2.5 includes the following steps: S2.5.1, Precursor Node Identification.

[0092] Based on the humidity vertical gradient calculated in step S2.4 Wind speed shear rate and Richardson number Precursor detection is performed on each grid node. For any given grid node... Based on the calculation results in step S2.4, extract the parameters corresponding to this node, and denot them as follows: , , Then, construct a decision function, expressed as the following formula.

[0093] (6).

[0094] (7).

[0095] (8).

[0096] in, , , These are the decision functions corresponding to the vertical humidity gradient, wind speed shear rate, and Richardson number, respectively. , , They are respectively , , The corresponding preset threshold.

[0097] Define node precursor judgment value It is expressed as the following formula.

[0098] (9).

[0099] When satisfied And the judgment condition is maintained for a continuous time exceeding a preset time threshold. T P When this occurs, the grid node is identified as a precursor node. The duration refers to the length of time during which the node's meteorological parameters continuously meet the precursor determination criteria.

[0100] S2.5.2 Calculation of confidence level of precursor signal.

[0101] For the aforementioned precursor node, extract its meteorological time-series data for the past 72 hours, including temperature T, humidity H, wind speed V, air pressure P, and the data calculated in step S2.4. , and The time series data is input into a pre-trained time series analysis model to obtain precursor probability values. Meanwhile, based on the degree of deviation of the meteorological parameters at the current time node from the threshold, a physical rule score is constructed, expressed as the following formula.

[0102] (10).

[0103] (11).

[0104] (12).

[0105] in, , , These are the physical rule scores corresponding to the vertical humidity gradient, wind speed shear rate, and Richardson number, respectively. ε It is a very small positive number.

[0106] Construct a comprehensive score for physical rules , expressed as the following formula.

[0107] (13).

[0108] (14).

[0109] in, , , They are respectively , , The corresponding weights.

[0110] The precursor probability value output by the time series model Combined score with physical rules Weighted fusion is performed to obtain the confidence level of the precursor signal. , expressed as the following formula.

[0111] (15).

[0112] in, The weights are the probability values ​​of the precursors, and .

[0113] S2.5.3 Calculation of the initial value of current meteorological disaster risk.

[0114] In this embodiment of the application, the number of precursor nodes is set to... The total number of nodes is Then the basic risk ratio It is expressed as the following formula.

[0115] (16).

[0116] Then calculate the average confidence level of the precursor nodes. The calculation formula is as follows.

[0117] (17).

[0118] Further obtain the initial value of current meteorological disaster risk , expressed as the following formula.

[0119] (18).

[0120] in, This is the confidence enhancement coefficient.

[0121] As one possible implementation, step S3 includes the following steps.

[0122] S3.1. The precursor nodes identified in step S2 are taken as disaster source nodes.

[0123] S3.2 Based on the meteorological disaster propagation network constructed in step S1, the Dijkstra algorithm is used to search for the target propagation path from the disaster source node to the grid node.

[0124] The disaster source node is the precursor node identified in step S2; the power station node is the grid node containing new energy power stations in the grid nodes divided in step S1.1.

[0125] As a feasible approach, the propagation cost between nodes is... Defined as the negative logarithm of the propagation probability: .

[0126] Then minimize the total path cost, expressed as the following formula.

[0127] (19).

[0128] Ultimately, the optimal propagation path from the disaster source node to the site node is obtained. , as the target propagation path.

[0129] S3.3, Based on the target propagation path Probability of disaster propagation between nodes P ij Based on historical average propagation speed, calculate the estimated arrival time of the disaster from the source node to the site node. T arr .

[0130] For the target propagation path Suppose it contains a sequence of nodes. Propagation time between adjacent nodes It is expressed as the following formula.

[0131] (20).

[0132] in, is the Euclidean distance between adjacent nodes. This represents the propagation speed between adjacent nodes.

[0133] The propagation speed is adjusted based on the historical average propagation speed and the meteorological differences between nodes, and is expressed as the following formula.

[0134] (twenty one).

[0135] in, For grid nodes i With grid nodes j The speed of transmission between them Let Δ be the initial propagation speed. T ij For grid nodes i With grid nodes j The temperature difference between them, Δ V ij For grid nodes i With grid nodes j The difference in wind speed between them α , β The propagation coefficient is obtained based on historical data training.

[0136] As an feasible approach, the estimated arrival time of a disaster from the source node to the site node is determined. T arr It is expressed as the following formula.

[0137] (twenty two).

[0138] S3.4, Propagate the target path The nodes on the map and the set of nodes whose propagation probability is greater than a preset threshold are collectively considered as the scope of disaster impact.

[0139] As one possible implementation, step S4 includes the following steps.

[0140] S4.1 Determine the basic risk ratio based on the number of affected nodes within the disaster's impact area and the total number of nodes in the propagation network. ,and ,in The number of affected nodes. This represents the total number of nodes.

[0141] S4.2 Introduce the confidence level of the precursor signal output in step S2. C ∈[0,1], relative to the basic risk ratio A comprehensive risk index is obtained by performing dynamic weighted adjustments. R , expressed as the following formula.

[0142] (twenty three).

[0143] in, This is the confidence enhancement coefficient, and 0 < γ ≤1 is used to reflect the amplifying effect of high-confidence precursors on risk levels. This is the time decay coefficient.

[0144] S4.3, Based on the comprehensive risk index R The warning levels are divided into four levels, including: (1) Ultra-low risk: R ≤0.5; (2) Low risk: 0.5< R ≤0.75; (3) Medium risk: 0.75< R ≤1.0; (4) High risk: R >1.0.

[0145] S4.4 Generate structured early warning signals as extreme weather warning results, including warning levels. L Comprehensive Risk Index R Confidence of precursor signals C Scope of impact Estimated arrival time T arr and the effective duration of the warning T valid .

[0146] In this embodiment of the application, the early warning data object is used to drive the triggering, execution and adjustment of subsequent prevention and control measures.

[0147] As one possible implementation, step S5 includes the following steps.

[0148] S5.1 Based on the structured early warning signal (i.e. extreme weather early warning result) output in step S4.4, use it as the basis for decision-making on prevention and control measures, and formulate prevention and control strategies.

[0149] S5.2, When the warning level L When the risk level is extremely low, the effective warning duration is [duration missing]. T valid The system will maintain the normal operation of the new energy power station, only push information prompts to the operation and maintenance personnel, and continuously track and monitor the meteorological parameters within the influence range Ω.

[0150] S5.3, When the warning level L When the risk is low, based on the confidence level of the precursor signals. C The influence range Ω is used to correct the input meteorological parameters in the power prediction model, and the effective duration of the warning is also considered. T valid The power prediction results are updated internally. The input meteorological parameters include wind speed parameters for wind power scenarios or irradiance parameters for photovoltaic scenarios. The correction reflects the disturbance impact of extreme weather precursors on the wind speed-power mapping or irradiance-power mapping in the affected area, thereby improving the robustness of the power prediction results and reducing scheduling bias.

[0151] As an implementable approach, adjusting the wind speed-power or irradiance-power mapping in the power prediction model further includes the following steps: (1) When the new energy power station is a wind farm, the input wind speed is corrected to obtain the corrected wind speed, which is expressed as the following formula.

[0152] (twenty four).

[0153] in, V Original wind speed, V′ This is the corrected wind speed. C The confidence level of the precursor signal.

[0154] Furthermore, the corrected wind speed V′ is input into the wind speed-power mapping relationship to obtain the updated predicted power.

[0155] (2) When the new energy power station is a photovoltaic power station, the input irradiance is corrected to obtain the corrected irradiance, which is expressed as the following formula.

[0156] (25).

[0157] in, Original irradiation intensity This is the corrected irradiance.

[0158] Furthermore, the corrected irradiance intensity By inputting the irradiance-power mapping relationship, the updated predicted power is obtained.

[0159] As an implementable approach, the above-described corrections are performed only on the input parameters within the affected region, depending on the influence range Ω.

[0160] S5.4, When the warning level L When the risk level is medium, it is determined according to the comprehensive risk index. R , the area of ​​impact Ω and the estimated time of arrival T arr Adjust the charging and discharging strategy of the energy storage system and at the expected arrival time. T arr Emergency capacity was reserved in advance to cope with possible power fluctuations or sudden drops within the affected range Ω.

[0161] S5.5, When the warning level L When it is considered high-risk, or at the expected arrival time T arr If the time is less than the preset time threshold, determine the equipment area requiring protective measures based on the impact range Ω, and implement these measures at the expected arrival time. T arrEmergency protective measures were previously performed on the equipment within the equipment area.

[0162] The emergency protection operations include at least one of the following: stopping the wind turbine feathering, leveling the photovoltaic support to a wind-resistant posture, and activating the automatic shading device for the photovoltaic panels.

[0163] The preset time threshold can be set according to the type of site, equipment response time, and historical disaster response experience.

[0164] S5.6 During the implementation of prevention and control measures, the effective duration of the early warning shall be considered. T valid The corresponding measures shall be maintained for the duration of the warning, and the corresponding prevention and control measures shall be lifted or downgraded when the effective period of the warning expires or when the warning level is detected to have decreased.

[0165] S5.7 Record the execution time, execution area, execution results, and changes in power of various prevention and control measures as feedback input for dynamic adjustment of model parameters in step S6.

[0166] As one possible implementation, step S6 includes the following steps.

[0167] S6.1 Collect the actual disaster evolution results (such as the actual impact range of the disaster and the arrival time) and equipment response results (such as whether the shutdown was successful and the power fluctuation range) after the implementation of prevention and control measures.

[0168] S6.2. Based on feedback data, update the propagation coefficient using an online learning algorithm (such as recursive least squares method). α , β .

[0169] S6.3 Optimize the disaster propagation probability model between nodes by combining newly added historical extreme weather event data.

[0170] S6.4. Based on the deviation between the actual disaster evolution and the predicted results, adjust the parameters in the calculation of the comprehensive risk index, including the confidence enhancement coefficient. and time decay coefficient This aims to improve the comprehensive risk index's ability to characterize disaster intensity and temporal characteristics.

[0171] S6.5. Based on the actual disaster evolution results, adjust the judgment thresholds in the precursor node identification process, including the humidity vertical gradient threshold, wind speed shear rate threshold, Richardson number threshold, and duration threshold, in order to improve the accuracy and stability of precursor identification.

[0172] S6.6. Based on the actual disaster evolution results and equipment response results, adjust the triggering conditions in the early warning and prevention and control strategies, including the early warning level classification threshold and the preset time threshold, in order to optimize the triggering timing of prevention and control measures.

[0173] Based on the above parameters, precursor nodes are identified, and meteorological data from the past preset time period (e.g., the past 72 hours) are input into the time series analysis model to output the confidence level of the precursor signal. C The current meteorological disaster risk is calculated by ∈[0,1]. This method can more accurately characterize the microscale atmospheric stability under complex terrain conditions.

[0174] This application's embodiments, by dividing the area surrounding the power station into nodes and constructing a meteorological disaster propagation network, can characterize the spatial propagation relationship of disasters and enhance the predictive ability of disaster propagation paths, arrival times, and impact ranges. By identifying precursor nodes based on multi-altitude meteorological parameters and calculating current meteorological disaster risks, the timeliness and accuracy of extreme weather precursor identification can be improved. By using current meteorological disaster risks, propagation paths, and impact ranges together to generate multi-level early warning signals, and using the impact range to guide regional prevention and control measures, the executability of early warning results for power prediction adjustments, energy storage optimization, and equipment protection can be improved. By introducing feedback from prevention and control results to dynamically update the propagation model and risk weights, the system's adaptability and early warning accuracy during long-term operation can be enhanced. The method of this application can realize the dynamic identification of extreme weather precursors, accurate risk assessment, and automatic execution of graded prevention and control for new energy power stations, effectively improving the safety and reliability of power station operation.

[0175] Based on the same inventive concept, this application also provides a system for identifying and warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks, used to implement the aforementioned method for identifying and warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks. The solution provided by this system is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the system for identifying and warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks provided below can be found in the limitations of the method for identifying and warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks described above, and will not be repeated here.

[0176] In one exemplary embodiment, such as Figure 3 As shown, a new energy power station extreme weather precursor identification and early warning system based on meteorological disaster propagation network is provided, which includes the following modules.

[0177] The propagation network construction module is used to acquire spatial geographic data of new energy power stations and construct a meteorological disaster propagation network.

[0178] The risk calculation module is used to monitor meteorological parameters of the corresponding areas of each grid node in real time, calculate the current meteorological disaster risk, and identify precursor nodes based on the meteorological parameters. This risk calculation module includes a data quality control unit, a parameter calculation unit, a threshold adjustment unit, a physical rule verification unit, and a time series analysis unit, which are used for data quality control, parameter calculation, threshold adjustment, physical rule verification, and time series analysis, respectively.

[0179] The propagation prediction module is used to predict the propagation path, estimated arrival time, and impact range of the disaster to the site by taking the precursor node as the disaster source node and combining it with the disaster propagation probability.

[0180] The early warning generation module is used to construct a comprehensive risk index based on the current meteorological disaster risk, the propagation path, the expected arrival time, and the scope of impact, and to generate multi-level early warning signals based on the comprehensive risk index.

[0181] The prevention and control execution module is used to implement phased prevention and control measures on the operation status of new energy power plants based on the multi-level early warning signals, the scope of impact, and the estimated arrival time of the disaster. This module includes a power prediction and adjustment unit, an energy storage control unit, and an equipment protection unit, which are used for power prediction and adjustment, energy storage control, and equipment protection, respectively.

[0182] The feedback adjustment module is used to dynamically adjust the parameters of the meteorological disaster propagation network based on the effectiveness of prevention and control measures and the actual evolution of the disaster.

[0183] The communication module is used to support multi-level communication within the new energy power station and between the new energy power station and the dispatch center or mobile terminal, ensuring the reliable transmission of early warning commands and control signals.

[0184] Through the synergistic effect of the above modules, it is possible to achieve dynamic identification of extreme weather precursors, accurate risk assessment, and automatic execution of graded prevention and control at new energy power plants, thereby improving the timeliness and accuracy of extreme weather precursor identification and early warning at new energy power plants and effectively enhancing the safety and reliability of power plant operation.

[0185] In one exemplary embodiment, another extreme weather precursor identification and early warning system for new energy power stations based on a meteorological disaster propagation network is provided. This system can be a computer device, which may be a server or a terminal, and its internal structure diagram can be as follows: Figure 4As shown, the 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 operation of the operating system and computer programs stored in the non-volatile storage media. The database stores spatial geographic data, historical meteorological data, and real-time meteorological data from the new energy power station. 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 the computer program is executed by the processor, it implements a method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network.

[0186] Figure 4 The structures shown are merely block diagrams of some structures related to the present application and do 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 shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0187] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0188] 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.

[0189] 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 related data must comply with relevant regulations and be authorized by the owner of the corresponding device.

[0190] 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).

[0191] 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.

[0192] 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.

[0193] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks, characterized in that, include: Acquire spatial geographic data, historical meteorological data, and real-time meteorological data of new energy power stations; Based on the aforementioned spatial geographic data, a meteorological disaster propagation network is constructed; The meteorological disaster propagation network is obtained by dividing the area around the new energy power station into spatial grids, with the new energy power station as the center. Each spatial grid in the meteorological disaster propagation network is defined as a grid node. Based on the historical meteorological data, the probability of disaster propagation between each grid node is calculated; the probability of disaster propagation is used to characterize the propagation relationship of extreme weather disasters between different grid nodes. Based on the real-time meteorological data and the historical meteorological data, identify the precursor nodes in the grid nodes and calculate the current meteorological disaster risk value of the precursor nodes; Using the precursor node as the disaster source node, and based on the meteorological disaster propagation network and the disaster propagation probability, the propagation path, estimated arrival time, and impact range of the disaster source node to the new energy power station are predicted; Based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the impact range, the extreme weather warning results and corresponding prevention and control measures and strategies are determined.

2. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 1, characterized in that, Based on the aforementioned spatial geographic data, a meteorological disaster propagation network is constructed, specifically including: Based on the spatial geographic data, the area around the new energy power station is divided into several spatial grids of a predetermined size, resulting in several grid nodes that constitute the meteorological disaster propagation network.

3. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 1, characterized in that, Based on the real-time meteorological data and the historical meteorological data, precursor nodes in the grid nodes are identified, and the current meteorological disaster risk value of the precursor nodes is calculated, specifically including: The real-time meteorological data is subjected to outlier removal, time synchronization correction, and deviation compensation to obtain corrected real-time meteorological data; Based on the corrected real-time meteorological data, the humidity vertical gradient, wind speed shear rate, and Richardson number are calculated respectively. Based on the humidity vertical gradient, the wind speed shear rate, and the Richardson number, identify precursor nodes in the grid nodes; Based on the historical meteorological data of the precursor nodes, combined with the humidity vertical gradient, the wind speed shear rate, and the Richardson number, the confidence level of the precursor signal is calculated. The current meteorological disaster risk is calculated based on the confidence level of the aforementioned precursor signals.

4. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 1, characterized in that, Using the precursor node as the disaster source node, and based on the meteorological disaster propagation network and the disaster propagation probability, the propagation path, estimated arrival time, and impact range from the disaster source node to the new energy power station are predicted, specifically including: Using the precursor nodes as disaster source nodes, and based on the meteorological disaster propagation network, the Dijkstra algorithm is used to search for the propagation path from the disaster source nodes to the grid nodes of the new energy power station; Based on the disaster propagation probability between each grid node along the propagation path and combined with the historical average propagation speed in the historical meteorological data, the estimated arrival time of the disaster at the new energy power station is calculated. Based on the disaster propagation probability among the grid nodes, a set of nodes with a disaster propagation probability greater than a preset threshold is determined, and the set of nodes is taken as the impact range of the disaster on the new energy power station.

5. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 3, characterized in that, Based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the affected area, the extreme weather warning results and corresponding prevention and control strategies are determined, specifically including: Determine the total number of nodes in the meteorological disaster propagation network and the number of affected nodes within the affected area; Calculate the basic risk ratio based on the total number of nodes and the number of affected nodes; Based on the confidence level of the precursor signals, the basic risk ratio is weighted and adjusted to obtain a comprehensive risk index; The warning levels are determined based on the comprehensive risk index, and extreme weather warning results are generated. The extreme weather warning results include the warning level, comprehensive risk index, confidence level of precursor signals, affected area, expected arrival time, and effective duration of the warning. Based on the extreme weather warning results, corresponding prevention and control measures and strategies will be formulated.

6. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 5, characterized in that, The warning levels include ultra-low risk, low risk, medium risk, and high risk; Based on the extreme weather warning results, corresponding prevention and control strategies are formulated, including: When the warning level is ultra-low risk, the new energy power station shall be kept in normal operation within the effective duration of the warning, and a reminder message shall be pushed to the operation and maintenance personnel. When the warning level is low risk, the input meteorological parameters in the power prediction model are corrected according to the confidence level of the precursor signal and the range of influence, and the power prediction results are updated within the effective duration of the warning; the power prediction model is a mapping model used to predict the power generation of the new energy power station based on meteorological parameters; When the warning level is medium risk, the charging and discharging strategy of the energy storage system of the new energy power station is adjusted according to the comprehensive risk index, the scope of impact and the estimated arrival time, and emergency capacity is reserved before the estimated arrival time. When the warning level is high risk, the equipment area that needs to be protected is determined according to the scope of impact, and emergency protection operations are performed on the equipment within the equipment area before the expected arrival time; the emergency protection operations include at least one of wind turbine feathering shutdown, photovoltaic bracket leveling, or automatic photovoltaic panel shading.

7. The method for identifying and issuing early warning of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks according to claim 5, characterized in that, After determining the extreme weather warning results and corresponding prevention and control strategies based on the current meteorological disaster risk value, the propagation path, the expected arrival time, and the impact range, the method for identifying and issuing early warnings of extreme weather precursors at new energy power stations based on meteorological disaster propagation networks further includes: Dynamically adjusting the network parameters of the meteorological disaster propagation network specifically includes: Collect the actual disaster evolution results and equipment response results after the implementation of prevention and control measures; Based on the actual disaster evolution results and the equipment response results, an online learning algorithm is used to update the propagation coefficient in the disaster propagation probability calculation process, and combined with newly added historical extreme weather event data, the disaster propagation probability model between network nodes is optimized. Based on the deviation between the actual disaster evolution results and the extreme weather warning results, adjust the confidence enhancement coefficient and time decay coefficient in the calculation process of the comprehensive risk index; Based on the actual disaster evolution results, the judgment thresholds in the precursor node identification process are adjusted; the judgment thresholds include humidity vertical gradient threshold, wind speed shear rate threshold, Richardson number threshold, and duration threshold; Based on the actual disaster evolution and the equipment response results, the triggering conditions in the prevention and control measures strategy are adjusted; the triggering conditions include a warning level classification threshold and a preset time threshold.

8. A system for identifying and issuing early warning of extreme weather precursors at new energy power stations based on a meteorological disaster propagation network, comprising: A memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes the computer program to implement the method for identifying and issuing early warning of extreme weather precursors for new energy power stations based on a meteorological disaster propagation network, as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the method for identifying and issuing early warnings of extreme weather precursors for new energy power stations based on a meteorological disaster propagation network, as described in any one of claims 1-7.

Images