A method, device, equipment and medium for preventing and controlling forest fires of a power transmission line

Abstract

The application discloses a mountain fire prevention and control method, device, equipment and medium of a power transmission line, which is applied to the power transmission line, obtains size information and line position information of the power transmission line under the influence of a mountain fire, determines a thermal balance parameter of the power transmission line under the influence of the mountain fire based on the size information, the line position information and mountain fire information of the mountain fire, and determines a thermal balance relationship of the power transmission line under the influence of the mountain fire by using the thermal balance parameter and an actual current of the power transmission line at present. Based on the thermal balance relationship, a dynamic rated current of the power transmission line under the influence of the mountain fire is determined, and a first failure probability of the power transmission line is determined based on the dynamic rated current and the actual current. According to the first failure probability, the mountain fire prevention and control of the power transmission line is carried out, the coupling of the fire radiation field of the mountain fire and the nonlinear decline of the cable thermal physical properties of the power transmission line is carried out for the mountain fire prevention and control, and the precision of the mountain fire prevention and control of the power transmission line is improved.

Description

Technical Field

[0001] This application relates to the field of power transmission, and in particular to a method, device, equipment and medium for preventing wildfires in power transmission lines. Background Technology

[0002] In related technologies, with the intensification of extreme global climate, frequent wildfires have become one of the core risks threatening the safe operation of power grids.

[0003] During wildfires, relevant technologies can collect micro-meteorological data around power grid transmission lines, such as temperature, humidity, and wind speed. Satellite remote sensing, drone inspections, or lidar technology can be used to measure the MVCD (Minimum Vegetation Clearance Distance) between the power grid transmission lines and surrounding vegetation. The minimum vegetation clearance distance refers to the minimum air gap distance that must be maintained between the power grid transmission lines and surrounding vegetation to prevent electrical breakdown.

[0004] Related technologies can predict the damage risk of wildfires to power transmission lines based on micro-meteorological data around the lines and the minimum vegetation safety distance. However, the damage caused by wildfires to power grid transmission lines is multi-dimensional. Considering only the minimum vegetation safety distance between the transmission lines and surrounding vegetation, as well as static meteorological data around the lines, without considering other dimensions of wildfire damage to the power grid, leads to a disconnect between the fire situation and the multi-physics failure of power grid equipment. This results in low accuracy in assessing the risk of wildfires to power grid operation safety, and consequently, insufficient precision in wildfire prevention and control measures for the power grid based on this risk. Summary of the Invention

[0005] This application provides a method, device, equipment, and medium for wildfire prevention and control of transmission lines, in order to solve the problem that the accuracy of the assessment of the power grid operation safety risk caused by wildfires is not high in related technologies, and therefore the wildfire prevention and control of the power grid based on the risk of wildfires to the operation safety of the power grid is not accurate enough.

[0006] To address the aforementioned technical problems, this application provides a method for preventing wildfires on power transmission lines, applicable to power transmission lines. The wildfire prevention method includes: Obtain the size and location information of power transmission lines affected by wildfires; Based on the size information, the line location information, and the wildfire information, the heat balance parameters of the transmission line under the influence of the wildfire are determined, and the heat balance parameters and the current actual current of the transmission line are used to determine the heat balance relationship of the transmission line under the influence of the wildfire. Based on the aforementioned thermal balance relationship, the dynamic rated current of the transmission line under the influence of the wildfire is determined, and based on the dynamic rated current and the actual current, the first fault probability of the transmission line is determined. Based on the first fault probability, wildfire prevention and control measures are implemented for the power transmission line.

[0007] In this embodiment, to address the operational risks of wildfires to power transmission lines, the size and location information of the affected transmission lines are obtained. Based on these information, the thermal balance parameters of the transmission lines under wildfire influence are determined. Using these parameters and the current actual current of the transmission lines, the thermal balance relationship is established, realizing the coupling between the wildfire's thermal radiation field and the thermophysical processes of the transmission lines. Based on this thermal balance relationship, the dynamic rated current of the transmission lines under wildfire influence is determined, enabling a quantitative assessment of the current-carrying capacity of the transmission lines under wildfire influence. Based on the dynamic rated current and actual current of the transmission lines, the first probability of failure is determined, coupling the wildfire's thermal radiation field with the nonlinear degradation of the cable's thermophysical properties. This quantitatively characterizes the performance degradation path of cable materials under accumulated thermal stress, improving the accuracy of predicting the risk of damage to power transmission lines caused by wildfires. Based on the first failure probability of transmission lines under the influence of wildfires, wildfire prevention and control of transmission lines is carried out, realizing an adaptive mapping from failure probability to prevention and control measures, and improving the accuracy of wildfire prevention and control of transmission lines.

[0008] As a preferred embodiment, the wildfire information includes fire source location information and environmental information surrounding the fire source; the heat balance parameters include the heat transferred from the wildfire to the transmission line; determining the heat balance parameters of the transmission line under the influence of the wildfire based on the size information, the line location information, and the wildfire information includes: Based on the fire source location information and the environmental information, the spread information of the wildfire during the burning process is determined, and based on the spread information, the edge location information of the wildfire at any time point during the burning process is determined; Based on the line location information and the wildfire edge location information, the heat flux from the wildfire to the transmission line is determined; Based on the heat flux and the size information, the amount of heat transferred from the wildfire to the power transmission line is determined.

[0009] In this embodiment, by fusing the fire source location information and the surrounding environmental information of a wildfire, the spread boundary of the wildfire is dynamically tracked, and the edge location information of the wildfire at any time point during the combustion process is determined. Based on the line location information of the power transmission line and the edge location information of the wildfire, the heat flux transferred from the wildfire to the power transmission line is determined, and based on this heat flux and the size information of the power transmission line, the amount of heat transferred from the wildfire to the power transmission line is determined. This achieves a refined spatiotemporal assessment of the heat transferred from the wildfire to the power transmission line, providing physically interpretable input parameters for predicting the first failure probability of the power transmission line under the influence of wildfire.

[0010] As a preferred embodiment, the heat balance parameters further include the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat of the transmission line under solar irradiation, and the current temperature of the transmission line under the influence of the wildfire; determining the heat balance relationship of the transmission line under the influence of the wildfire using the heat balance parameters and the current actual current of the transmission line includes: Based on the current temperature, determine the resistance of the transmission line at the current temperature; The thermal balance relationship of the transmission line under the influence of the wildfire is determined by using the resistance, the convective heat loss rate, the radiative heat loss rate, the solar radiation heat, the heat transferred from the wildfire to the transmission line, and the actual current.

[0011] In this embodiment, the thermal balance relationship of the transmission line under the influence of wildfire is determined by using the resistance of the transmission line at the current temperature under the influence of wildfire, the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat, the heat transferred to the transmission line by the wildfire, and the current actual current of the transmission line. This achieves a complete consideration of the combined effect of multiple heat sources, improving the reliability and rationality of predicting the probability of line failure under wildfire conditions based on the thermal balance relationship.

[0012] As a preferred embodiment, determining the first fault probability of the transmission line based on the dynamic rated current and the actual current includes: Determine whether the difference between the dynamic rated current and the actual current is less than a preset current threshold. If the difference between the dynamic rated current and the actual current is less than the current threshold, then the first fault probability of the transmission line is determined based on the preset shape parameters of the transmission line, the dynamic rated current, and the actual current.

[0013] In this embodiment of the application, if the difference between the dynamic rated current and the actual current is less than the current threshold, it is considered that the dynamic rated current of the transmission line under the influence of wildfire is close to or less than the actual current, thus determining the risk of the transmission line having a first fault. In the case of the risk of the transmission line having a first fault, the probability of the transmission line having a first fault under the influence of wildfire is determined, thereby improving the accuracy of predicting the risk of damage to the transmission line by wildfire.

[0014] As a preferred embodiment, the wildfire prevention and control method further includes: Based on the initial temperature of the transmission line before the wildfire occurred and the current temperature of the transmission line under the influence of the wildfire, the temperature rise data of the transmission line under the influence of the wildfire is determined; Using the current temperature, the temperature rise data, and the preset tensile strength loss ratio parameter of the transmission line under the influence of the wildfire, the life loss parameter of the transmission line under the influence of the wildfire is determined; Using the aforementioned life loss parameters, the safe operating time of the transmission line under the influence of the wildfire is predicted; Based on the safe operating time and the preset target operating time of the transmission line, the second failure probability of the transmission line under the influence of the wildfire is determined; Wildfire prevention and control measures are implemented for the power transmission line based on the second fault probability and the first fault probability.

[0015] In this embodiment, the current temperature, temperature rise data, and tensile strength loss ratio of the transmission line under the influence of wildfires are used to determine the lifespan loss parameters of the transmission line under the influence of wildfires. This quantifies the impact of the high temperature of wildfires accelerating the thermal aging process of cables. This thermal aging process significantly increases the risk of cable sagging due to heat, leading to wire contact flashover and thus endangering the lifespan of the transmission line. Using the lifespan loss parameters, the safe operating time of the transmission line under the influence of wildfires can be predicted. Based on this safe operating time and the preset target operating time of the line, the second failure probability of the transmission line under the influence of wildfires is determined. This scheme realizes the coupled analysis of the thermal radiation field of wildfires and the nonlinear decay of the thermophysical properties of cables, further improving the accuracy of predicting the risk of damage to transmission lines by wildfires. Based on the aforementioned first and second failure probabilities of the transmission line under the influence of wildfires, wildfire prevention and control measures are implemented for the transmission line, thereby further improving the accuracy of wildfire prevention and control.

[0016] As a preferred embodiment, the power transmission line is erected above the combustible material; the wildfire is formed by the combustion of the combustible material; the power transmission line includes at least two parallel transmission conductors; the at least two parallel transmission conductors are located on the same plane parallel to the ground; the wildfire prevention and control method further includes: Determine the burning height data of the wildfire, the height difference between the power transmission line and the combustible material, and the distance between the at least two parallel power transmission lines; Based on the combustion height data, the height difference, and the distance between the power transmission lines, the breakdown probability of the power transmission line under the influence of the wildfire is determined; the breakdown probability includes a first breakdown probability between the power transmission lines and a second breakdown probability of the power transmission line relative to the ground; Based on the first breakdown probability and the second breakdown probability, a third fault probability of the transmission line under the influence of the wildfire is determined. Wildfire prevention and control measures are implemented for the power transmission line based on the third fault probability, the second fault probability, and the first fault probability.

[0017] In this embodiment of the application, based on the burning height data of wildfires, the height difference between power transmission lines and combustibles, and the distance between at least two parallel power transmission conductors, the breakdown probability of power transmission lines under the influence of wildfires is determined. The breakdown probability includes the first breakdown probability between power transmission conductors and the second breakdown probability of power transmission lines relative to the ground. This realizes the consideration of the electrical breakdown effect caused by wildfires at extremely close distances, that is, the flames themselves have high conductivity, and the high temperature and smoke containing a large amount of ash they generate will significantly reduce the air insulation performance between power transmission lines and the ground, as well as the air insulation performance between power transmission conductors.

[0018] In this embodiment, based on the first and second breakdown probabilities, the third fault probability of the transmission line under the influence of wildfire is determined. Based on the third fault probability, the second fault probability, and the first fault probability, the third wildfire prevention and control strategy for the transmission line is determined. This not only incorporates the dynamic rated current and cable thermal aging effect during the fire spread process into the fault probability assessment system, but also introduces the air insulation breakdown model caused by wildfire flames and high-temperature smoke. This achieves the accurate prediction of the fault probability of the transmission line in the rapidly evolving and highly complex extreme wildfire scenario by precisely quantifying the comprehensive tripping fault probability caused by the increase in line sag and the sharp decline in insulation performance under extreme high temperature environment.

[0019] As a preferred embodiment, determining the breakdown probability of the power transmission line under the influence of the wildfire based on the combustion height data, the height difference, and the distance between the power transmission conductors includes: Obtain the flame tolerance parameters of the transmission line to the wildfire, and determine the smoke tolerance parameters of the transmission line to the smoke from the wildfire. Determine whether the combustion height data is greater than the height difference value; If the combustion height data is greater than the height difference, then the breakdown probability of the power transmission line is determined by using the height difference, the distance between the power transmission conductors, and the flame tolerance parameter. If the combustion height data is less than the height difference, the breakdown probability of the transmission line is determined using the combustion height data, the height difference, the distance between the transmission conductors, the flame tolerance parameter, and the smoke tolerance parameter.

[0020] In this embodiment, the breakdown factor of the electrical insulation of the transmission line is determined based on the burning height data of the wildfire and the height difference between the transmission line and the combustible material. If the burning height data is greater than the height difference, the breakdown factor is the wildfire; if the burning height data is less than the height difference, the breakdown factors are the wildfire and smoke. Based on different breakdown factors, different methods for determining the breakdown probability are used, including wildfire burning height data, the height difference between the transmission line and the combustible material, the distance between transmission conductors, the flame tolerance parameters of the transmission line, and the smoke tolerance parameters of the smoke. This improves the accuracy of the breakdown probability prediction. Based on the first and second breakdown probabilities of the transmission line, the third fault probability of the transmission line under the influence of wildfire is determined, achieving accurate prediction of the line tripping failure rate.

[0021] As a preferred embodiment, the step of implementing wildfire prevention and control for the transmission line based on the third fault probability, the second fault probability, and the first fault probability includes: Based on the third fault probability, the second fault probability, and the first fault probability, the target fault probability of the transmission line under the influence of the wildfire is determined. Obtain the power supply information of the transmission line to the preset electrical equipment; The target failure probability, the spread information of the wildfire during the burning process, and the power supply information are input into a preset wildfire prevention and control model to obtain a wildfire prevention and control strategy. According to the aforementioned wildfire prevention and control strategy, wildfire prevention and control measures are implemented on the power transmission lines.

[0022] In this embodiment, the target failure probability of the transmission line under the influence of wildfire is determined based on the third failure probability, the second failure probability, and the first failure probability of the transmission line; the power supply information of the transmission line to the preset electrical equipment is obtained; the target failure probability, the spread information of the wildfire during the combustion process, and the power supply information are input into the preset wildfire prevention and control model to obtain the wildfire prevention and control strategy. This realizes the comprehensive consideration of the dynamic rated current during the fire spread process, the thermal aging effect of the cable, and the air insulation breakdown of the transmission line caused by the wildfire flames and high-temperature smoke, and determines the wildfire prevention and control strategy of the transmission line, thus achieving precise wildfire prevention and control.

[0023] As a preferred embodiment, the wildfire prevention and control method further includes: The training target failure probability of the transmission line under the influence of a preset training wildfire is obtained, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line for the training wildfire. The wildfire prevention and control model is obtained by training a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy.

[0024] In this embodiment, the initial neural network model is trained using the training target fault probability of the transmission line under the influence of a training wildfire, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line against the training wildfire. This enables the construction of a wildfire prevention and control model, which in turn enables the intelligent output of prevention and control strategies for the transmission line under wildfire disasters.

[0025] As a preferred embodiment, the step of training a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy to obtain the wildfire prevention and control model includes: The initial neural network model is updated using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain an updated neural network model. The updated neural network model is determined to output an inference and prevention strategy for the training wildfire based on the training target failure probability, the training power supply information, and the training spread information; the inference and prevention strategy includes cutting off the power supply to the transmission line or maintaining the power supply to the transmission line. Determine the fire risk cost of maintaining power supply to the transmission line according to the aforementioned reasoning and prevention strategy; Determine the load loss cost under the condition that the power supply to the transmission line is cut off according to the aforementioned reasoning and prevention strategy; Based on the fire risk cost and the load loss cost, determine the initial evaluation score of the reasoning prevention and control strategy, and based on the initial evaluation score, determine whether the updated neural network model meets the preset model training objective; If the updated neural network model satisfies the model training objective, then the updated neural network model will be used as the wildfire prevention and control model.

[0026] In this embodiment, when determining whether the updated neural network model meets the model training objective, the fire risk cost and load loss cost of the inference prevention and control strategy output by the updated neural network model are comprehensively considered to determine the initial evaluation score of the inference prevention and control strategy, and to determine whether the updated neural network model meets the model training objective. This allows the trained wildfire prevention and control model to comprehensively consider the fire risk cost and load loss cost, and output the transmission line's wildfire prevention and control strategy. This solves the problem in related technologies where, when the risk level of a wildfire to the normal operation of a specific transmission line of the power grid exceeds the safety threshold, directly cutting off the power transmission of that line often leads to over-defense against wildfire risks, causing large-scale and long-term unnecessary power outages and resulting in huge socio-economic losses.

[0027] In this embodiment, the target failure probability of the transmission line under the influence of wildfire, the spread information of the wildfire during the burning process, and the power supply information of the transmission line to the electrical equipment are input into the wildfire prevention and control model to obtain the wildfire prevention and control strategy of the transmission line. This realizes that the wildfire prevention and control strategy can be changed according to the spread information of the wildfire during the burning process. At the same time, based on the predicted time and intensity probability of the fire reaching the transmission line, the optimal balance path is found between "maximizing the continuous power supply" and "minimizing the risk of equipment burnout and secondary disasters" in multiple time periods. Thus, the disaster prevention strategy is upgraded from static passive response to forward-looking dynamic control, which solves the problem that the existing wildfire defense methods are too crude and lack multi-time period refined decision-making based on high-precision spatiotemporal extrapolation.

[0028] As a preferred embodiment, determining whether the updated neural network model meets the preset model training objective based on the initial evaluation score includes: When the training wildfire is controlled according to the aforementioned reasoning and control strategy, the inference current of the transmission line is determined. If the inference current is not less than the dynamic rated current, then the initial evaluation score is reduced by using a preset safety cost function to obtain the target evaluation score; If the target evaluation score is not less than the preset evaluation score threshold, then the updated neural network model is confirmed to meet the model training objective.

[0029] In this embodiment, when training wildfire prevention and control strategies according to the inference prevention and control strategies output by the updated neural network model, the inference current of the transmission line is determined. Under the condition that the inference current is not less than the dynamic rated current, the initial evaluation score is reduced by using a safety cost function to obtain the target evaluation score of the inference prevention and control strategy. The model is optimized based on the target evaluation score. This achieves the goal that, during the model training process, the prevention and control strategy output by the wildfire prevention and control model can ensure that the current of the transmission line is less than the dynamic rated current when controlling wildfires, so as to ensure the safe operation of the transmission line under the influence of wildfires.

[0030] This application also discloses a wildfire prevention device for power transmission lines, applied to power transmission lines, the wildfire prevention device comprising: The acquisition module is used to acquire the size and location information of power transmission lines affected by wildfires. The thermal balance relationship determination module is used to determine the thermal balance parameters of the transmission line under the influence of the wildfire based on the size information, the line location information and the wildfire information, and to determine the thermal balance relationship of the transmission line under the influence of the wildfire using the thermal balance parameters and the current actual current of the transmission line. The first fault probability determination module is used to determine the dynamic rated current of the transmission line under the influence of the wildfire based on the thermal balance relationship, and to determine the first fault probability of the transmission line based on the dynamic rated current and the actual current. The first wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the first fault probability.

[0031] As a preferred embodiment, the wildfire information includes fire source location information and environmental information surrounding the fire source; the heat balance parameters include the heat transferred from the wildfire to the power transmission line; the heat balance relationship determination module includes: The wildfire edge location information determination submodule is used to determine the spread information of the wildfire during the combustion process based on the fire source location information and the environmental information, and to determine the wildfire edge location information at any time point during the combustion process based on the spread information; The heat flux determination submodule is used to determine the heat flux transmitted from the wildfire to the transmission line based on the line location information and the wildfire edge location information; The heat determination submodule is used to determine the heat transferred from the wildfire to the power transmission line based on the heat flux and the size information.

[0032] As a preferred embodiment, the heat balance parameters further include the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat of the transmission line under solar irradiation, and the current temperature of the transmission line under the influence of the wildfire; the heat balance relationship determination module includes: A resistance determination submodule is used to determine the resistance of the transmission line at the current temperature based on the current temperature. The thermal balance relationship determination submodule is used to determine the thermal balance relationship of the transmission line under the influence of the wildfire by using the resistance, the convective heat loss rate, the radiative heat loss rate, the solar radiation heat, the heat transferred from the wildfire to the transmission line, and the actual current.

[0033] As a preferred embodiment, the first fault probability determination module includes: The current threshold determination submodule is used to determine whether the difference between the dynamic rated current and the actual current is less than a preset current threshold. The first fault probability determination submodule is used to determine the first fault probability of the transmission line based on the preset shape parameters of the transmission line, the dynamic rated current, and the actual current if the difference between the dynamic rated current and the actual current is less than the current threshold.

[0034] As a preferred embodiment, the wildfire prevention and control device further includes: The temperature rise data determination module is used to determine the temperature rise data of the transmission line under the influence of the wildfire based on the preset initial temperature of the transmission line before the wildfire occurred and the current temperature of the transmission line under the influence of the wildfire. The lifespan loss parameter determination module is used to determine the lifespan loss parameters of the transmission line under the influence of the wildfire by using the current temperature, the temperature rise data and the tensile strength loss ratio parameter preset by the transmission line under the influence of the wildfire. The safe operating time prediction module is used to predict the safe operating time of the transmission line under the influence of the wildfire using the life loss parameters. The second fault probability determination module is used to determine the second fault probability of the transmission line under the influence of the wildfire based on the safe operating time and the preset target operating time of the transmission line. The second wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the second fault probability and the first fault probability.

[0035] As a preferred embodiment, the power transmission line is erected above the combustible material; the wildfire is formed by the combustion of the combustible material; the power transmission line includes at least two parallel transmission conductors; the at least two parallel transmission conductors are located on the same plane parallel to the ground; the wildfire prevention device further includes: The distance determination module is used to determine the burning height data of the wildfire, the height difference between the power transmission line and the combustible material, and the distance between the at least two parallel power transmission lines; A breakdown probability determination module is used to determine the breakdown probability of the power transmission line under the influence of the wildfire based on the burning height data, the height difference, and the distance between the power transmission conductors; the breakdown probability includes a first breakdown probability between the power transmission conductors and a second breakdown probability of the power transmission line relative to the ground; The third fault probability determination module is used to determine the third fault probability of the transmission line under the influence of the wildfire based on the first breakdown probability and the second breakdown probability. The third wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the third fault probability, the second fault probability, and the first fault probability.

[0036] As a preferred embodiment, the breakdown probability determination module includes: The tolerance parameter acquisition submodule is used to acquire the flame tolerance parameters of the transmission line to the wildfire and determine the smoke tolerance parameters of the transmission line to the smoke from the wildfire. The height determination submodule is used to determine whether the combustion height data is greater than the height difference value; The first breakdown probability determination submodule is used to determine the breakdown probability of the power transmission line by using the height difference, the distance between the power transmission conductors, and the flame tolerance parameter if the combustion height data is greater than the height difference. The second breakdown probability determination submodule is used to determine the breakdown probability of the transmission line by using the combustion height data, the height difference, the distance between the transmission conductors, the flame tolerance parameter, and the smoke tolerance parameter if the combustion height data is less than the height difference value.

[0037] As a preferred embodiment, the third wildfire prevention module includes: The target failure probability determination submodule is used to determine the target failure probability of the transmission line under the influence of the wildfire based on the third failure probability, the second failure probability and the first failure probability. The power supply information acquisition submodule is used to acquire the power supply information of the transmission line to the preset electrical equipment; The strategy acquisition submodule is used to input the target failure probability, the spread information of the wildfire during the combustion process, and the power supply information into a preset wildfire prevention and control model to obtain a wildfire prevention and control strategy; The wildfire prevention and control submodule is used to carry out wildfire prevention and control on the transmission line according to the wildfire prevention and control strategy.

[0038] As a preferred embodiment, the wildfire prevention and control device further includes: The training information acquisition submodule is used to acquire the training target failure probability of the transmission line under the influence of a preset training wildfire, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line for the training wildfire. The training submodule is used to train a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy to obtain the wildfire prevention and control model.

[0039] As a preferred embodiment, the training submodule includes: The update unit is used to update the initial neural network model using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain an updated neural network model. An inference strategy output unit is used to determine the inference prevention and control strategy for the training wildfire output by the updated neural network model based on the training target fault probability, the training power supply information, and the training spread information; the inference prevention and control strategy includes cutting off the power supply to the transmission line or maintaining the power supply to the transmission line; A fire risk cost determination unit is used to determine the fire risk cost of maintaining the power supply of the transmission line in accordance with the reasoning and prevention strategy. A load loss cost determination unit is used to determine the load loss cost under the condition that the power supply to the transmission line is cut off according to the reasoning and prevention strategy; The initial evaluation score determination unit is used to determine the initial evaluation score of the reasoning prevention and control strategy based on the fire risk cost and the load loss cost, and to determine whether the updated neural network model meets the preset model training objective based on the initial evaluation score. The model is used as a unit to take the updated neural network model as the wildfire prevention and control model if the updated neural network model meets the model training objective.

[0040] As a preferred embodiment, the initial evaluation score determination unit includes: The inference current determination subunit is used to determine the inference current of the transmission line when the training wildfire is controlled according to the inference control strategy. The target evaluation score is obtained by sub-units, which are used to reduce the initial evaluation score by using a preset safety cost function if the inference current is not less than the dynamic rated current, so as to obtain the target evaluation score. The model training objective confirmation subunit is used to confirm that the updated neural network model meets the model training objective if the objective evaluation score is not less than a preset evaluation score threshold.

[0041] This application also discloses an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in this application.

[0042] This application also discloses a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in this application. Attached Figure Description

[0043] Figure 1 This is a flowchart illustrating the steps of a method for preventing wildfires on power transmission lines, as provided in an embodiment of this application. Figure 2 This is a structural block diagram of a wildfire prevention device for a power transmission line provided in the embodiments of this application. Detailed Implementation

[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0045] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0046] To facilitate understanding of the technical solutions and effects of the embodiments of this application, the relevant technologies of this application will be briefly described below.

[0047] In related technologies, with the intensification of extreme global weather, frequent wildfires have become one of the core risks threatening the safe operation of power grids. On the one hand, electrical faults in power grid equipment (such as line flashovers) may become ignition sources for wildfires; on the other hand, wildfires spreading around power grid equipment may damage the power grid's transmission corridors, leading to widespread power outages.

[0048] To address the threat of wildfires to power grid operations, relevant technologies can predict the risk of wildfires ignited by electrical faults in the power grid. Specifically, these technologies can collect micro-meteorological data around power grid transmission lines and the minimum safe vegetation distance between transmission lines and surrounding vegetation. If the distance between the transmission line and surrounding vegetation is less than the minimum safe vegetation distance, an electrical fault in the power grid equipment may become an ignition source for a wildfire. These technologies can combine the minimum safe vegetation distance of the transmission line, the geometric data of the vegetation around the transmission line, and micro-meteorological data (such as temperature, humidity, and wind speed) to construct a static or semi-dynamic wildfire risk distribution map of the transmission line, predicting the risk of the power grid becoming an ignition source for wildfires. The wildfire risk distribution map indicates the wildfire risk level of different sections of the transmission line, guiding the regular inspection of power grid equipment and the clearing of vegetation around power grid equipment.

[0049] To address the threat of wildfires to power grid operations, related technologies can also implement proactive defense against wildfires. When the risk of wildfires jeopardizing normal grid operation is high, technologies such as Preventive Proactive Power Shutoff (PSPS) can be employed. When the risk level of a wildfire to the normal operation of a specific transmission line exceeds a safety threshold, power transmission on that line can be directly cut off, preventing secondary fires from occurring at the source. However, this power outage mode based on static safety thresholds is characterized by a "black and white" or "one-size-fits-all" approach, often leading to over-defense against wildfire risks, causing large-scale, prolonged, and unnecessary power outages, resulting in significant socio-economic losses. Furthermore, proactive defense control based on pre-set empirical rules using static safety thresholds involves massive computational demands and slow decision-making, making it difficult to meet the needs of proactive defense against wildfires at the second or minute level.

[0050] Reference Figure 1 This document illustrates a flowchart of the steps involved in a wildfire prevention method for power transmission lines, as provided in an embodiment of this application. The method is applied to power transmission lines and may specifically include the following steps: Step 101: Obtain the size and location information of the transmission lines affected by the wildfire; In this embodiment, a transmission line can refer to a power grid transmission line. A power grid may have at least one transmission line. A transmission line may include towers, transmission conductors, etc. The spatial whole consisting of the transmission line and the surrounding strip-shaped area (including land, vegetation, buildings, and other environmental elements) can be called a transmission corridor. The vegetation and other environmental elements around the transmission line may catch fire, potentially causing wildfires and threatening the normal operation of the transmission line.

[0051] In this embodiment of the application, a drone equipped with a lidar can be used to collect laser point cloud data of power transmission lines affected by wildfires, and the size and location information of the power transmission lines can be determined based on the laser point cloud data.

[0052] Step 102: Based on the size information, the line location information, and the wildfire information, determine the heat balance parameters of the transmission line under the influence of the wildfire, and use the heat balance parameters and the current actual current of the transmission line to determine the heat balance relationship of the transmission line under the influence of the wildfire. In this embodiment of the application, under the influence of wildfires, a thermal equilibrium relationship can be formed between the power grid transmission lines, the wildfires, and the surrounding environment.

[0053] In this embodiment of the application, wildfire information can be obtained through satellite remote sensing or other alarm monitoring technologies, and the impact of wildfire on power transmission lines can be determined based on the size information of power transmission lines, the location information of power transmission lines, and the wildfire information, so as to determine the heat balance parameters of power transmission lines under the influence of wildfire.

[0054] In this embodiment of the application, the current actual current of the transmission line can be obtained through the power grid dispatch center, and the thermal balance relationship of the transmission line under the influence of wildfire can be determined by using thermal balance parameters and the current actual current of the transmission line.

[0055] In some embodiments of this application, the wildfire information includes fire source location information and environmental information surrounding the fire source; the heat balance parameter includes the heat transferred from the wildfire to the transmission line; determining the heat balance parameter of the transmission line under the influence of the wildfire based on the size information, the line location information, and the wildfire information includes: Based on the fire source location information and the environmental information, the spread information of the wildfire during the burning process is determined, and based on the spread information, the edge location information of the wildfire at any time point during the burning process is determined; Based on the line location information and the wildfire edge location information, the heat flux from the wildfire to the transmission line is determined; Based on the heat flux and the size information, the amount of heat transferred from the wildfire to the power transmission line is determined.

[0056] In this embodiment of the application, the wildfire information may include the location information of the wildfire source and the environmental information surrounding the fire source. The environmental information surrounding the fire source may include the terrain around the fire source, the location of combustibles around the fire source, and meteorological information around the fire source, which may include temperature, wind speed, wind direction, and humidity, etc.

[0057] In this embodiment of the application, in order to determine the spread information of a wildfire during its combustion process, the geographical area covered by the power grid transmission lines can be digitally rasterized, dividing the geographical area into several cells of equal size, such as a 0.5km*0.5km grid. km refers to a kilometer.

[0058] Based on the fire source location information, the initial cell where the wildfire originates can be determined. Then, based on the fire source location information and the surrounding environmental information, the Wang Zhengfei model can be used to calculate the wildfire ignition state of the eight neighboring grids of each initial cell, and iterative calculations can be performed to simulate the spread of the fire over time, determining the spread information of the wildfire during combustion. The simulation time span is typically set to several hours in the future (e.g., 72 hours), and the simulation step size can be set to 30 minutes. Based on the wildfire spread information during combustion, the edge location information of the wildfire at any time point during combustion can be determined.

[0059] In this embodiment of the application, since the power grid may include at least one transmission line, the transmission line affected by the wildfire can be identified, and the spherical distance between the edge of the wildfire and the transmission line can be determined based on the line location information of the transmission line and the wildfire edge location information at the current time.

[0060] In this embodiment, the heat balance parameters of the transmission line under the influence of wildfire include the heat transferred from the wildfire to the transmission line. The heat transferred from the wildfire to the transmission line is mainly determined by the heat flux transferred from the wildfire to the transmission line and the size information of the transmission line. The size information of the transmission line can refer to the outer diameter of the transmission conductor.

[0061] In this embodiment of the application, the heat flux from a wildfire to a power transmission line can be transferred via radiative heat. and convective heat transfer It consists of two parts, or it can consist of only radiative heat transfer. The formula for calculating radiative heat transfer can be: in, It is atmospheric transmittance; It is the flame emissivity; It is the Stefan–Boltzmann constant; It is the flame temperature of a wildfire, which can be calculated using the Wang Zhengfei model; It is a perspective factor that reflects the geometrical relative position between the flame and the power transmission line; This refers to the distance between the edge of the wildfire and the power transmission line; This is the view of the power transmission line from the perspective of the wildfire.

[0062] The formula for calculating the viewing angle is: in, The height of the power transmission line.

[0063] Therefore, the height of the transmission conductor can be determined based on the location information of the transmission line, and the viewing angle of the transmission conductor relative to the wildfire can be determined using a formula based on the spherical distance between the wildfire edge and the transmission line. Next, based on the viewing angle of the transmission conductor relative to the wildfire and the spherical distance between the wildfire edge and the transmission line, a formula for calculating radiative heat transfer can be used to determine the radiative heat transfer from the wildfire to the transmission line, and this radiative heat transfer can be taken as the heat flux from the wildfire to the transmission line.

[0064] In this embodiment, based on the heat flux from the wildfire to the transmission line and the outer diameter of the transmission conductor, the heat transferred from the wildfire to the transmission line can be determined using a heat transfer calculation formula. The heat transfer calculation formula can be: in, Heat from wildfires is transferred to power transmission lines; The outer diameter of the power transmission line; This refers to the heat flux transferred from wildfires to power transmission lines.

[0065] In this embodiment, by fusing the fire source location information and the surrounding environmental information of a wildfire, the spread boundary of the wildfire is dynamically tracked, and the edge location information of the wildfire at any time point during the combustion process is determined. Based on the line location information of the power transmission line and the edge location information of the wildfire, the heat flux transferred from the wildfire to the power transmission line is determined, and based on this heat flux and the size information of the power transmission line, the amount of heat transferred from the wildfire to the power transmission line is determined. This achieves a refined spatiotemporal assessment of the heat transferred from the wildfire to the power transmission line, providing physically interpretable input parameters for predicting the first failure probability of the power transmission line under the influence of wildfire.

[0066] In some embodiments of this application, the heat balance parameters further include the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat of the transmission line under solar irradiation, and the current temperature of the transmission line under the influence of the wildfire; determining the heat balance relationship of the transmission line under the influence of the wildfire using the heat balance parameters and the current actual current of the transmission line includes: Based on the current temperature, determine the resistance of the transmission line at the current temperature; The thermal balance relationship of the transmission line under the influence of the wildfire is determined by using the resistance, the convective heat loss rate, the radiative heat loss rate, the solar radiation heat, the heat transferred from the wildfire to the transmission line, and the actual current.

[0067] In this embodiment, the convective heat loss rate of the transmission line can be determined using the formula for calculating the convective heat loss rate, and this convective heat loss rate can be used as a heat balance parameter. The formula for calculating the convective heat loss rate is: in, For convective heat loss rate, For wind direction factor, Let Reynolds number be 1. The thermal conductivity of air, This represents the current temperature of the transmission line. The ambient temperature.

[0068] In this embodiment, the radiative heat loss rate of the transmission line can be determined using the formula for calculating the radiative heat loss rate, and this radiative heat loss rate can be used as a heat balance parameter. The formula for calculating the radiative heat loss rate is: in, For radiative heat loss rate, The outer diameter of the power transmission line. The emissivity of the conductor.

[0069] In this embodiment, the solar radiation heat of the transmission line under sunlight and the current temperature of the transmission line under the influence of wildfires can also be considered as thermal balance parameters. Solar radiation heat is relatively stable and is mainly affected by the intensity of sunlight and the material of the transmission conductor. The formula for calculating solar radiation heat can be: in, Heat from solar radiation The outer diameter of the power transmission line; The solar radiation absorptivity of the transmission line; Solar radiation power density, measured in W / m³ 2 (watts per square meter), depending on the specific type of transmission line, typically ranges from 0.27 to 0.95, and can be 0.5.

[0070] In this embodiment, the current temperature of the transmission line under the influence of a wildfire can be collected, and the resistance of the transmission line at that temperature can be determined based on the material properties of the transmission line. Using resistance, convective heat loss rate, radiative heat loss rate, solar radiation heat, heat transferred from the wildfire to the transmission line, and actual current, a heat balance equation for the transmission line under the influence of a wildfire can be constructed. This heat balance equation can illustrate the heat balance relationship of the transmission line under the influence of a wildfire.

[0071] The first issue concerning the impact of wildfires on the power grid The first power transmission corridor Section of transmission line, during the time period The heat balance equation constructed within can be: in, For resistance, This is the actual current. The heat from the wildfire is transferred to the power transmission lines. Heat from solar radiation For convective heat loss rate, This represents the radiative heat loss rate.

[0072] In this embodiment, the thermal balance relationship of the transmission line under the influence of wildfire is determined by using the resistance of the transmission line at the current temperature under the influence of wildfire, the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat, the heat transferred to the transmission line by the wildfire, and the current actual current of the transmission line. This achieves a complete consideration of the combined effect of multiple heat sources, improving the reliability and rationality of predicting the probability of line failure under wildfire conditions based on the thermal balance relationship.

[0073] Step 103: Based on the heat balance relationship, determine the dynamic rated current of the transmission line under the influence of the wildfire, and based on the dynamic rated current and the actual current, determine the first fault probability of the transmission line. In this embodiment, the dynamic rated current of the transmission line under the influence of a wildfire can be determined based on the heat balance equation of the transmission line. The dynamic rated current refers to the maximum instantaneous current allowed to flow through the transmission line under specific wildfire conditions to ensure its safe operation without damage. Therefore, the dynamic rated current reflects the impact of wildfires on the transmission line, and the first probability of failure of the transmission line under the influence of a wildfire can be determined based on the dynamic rated current and the current actual current of the transmission line.

[0074] In some embodiments of this application, determining the first fault probability of the transmission line based on the dynamic rated current and the actual current includes: Determine whether the difference between the dynamic rated current and the actual current is less than a preset current threshold. If the difference between the dynamic rated current and the actual current is less than the current threshold, then the first fault probability of the transmission line is determined based on the preset shape parameters of the transmission line, the dynamic rated current, and the actual current.

[0075] In this application embodiment, the dynamic rated current can also be referred to as DTR (Dynamic Thermal Rating). The first fault probability of a transmission line under the influence of wildfires can refer to the first tripping fault rate of the transmission line.

[0076] In this embodiment of the application, the calculation formula for the dynamic rated current of the transmission line can be determined based on the heat balance equation. The first [unit / item] affected by wildfires... The first power transmission corridor Section of transmission line, during the time period The formula for calculating the dynamic rated current is: in, This refers to the dynamic rated current.

[0077] In this embodiment, the dynamic rated current calculation formula can be used to determine the dynamic rated current of the transmission line under the influence of wildfire, and based on the dynamic rated current and the actual current, it can be determined whether there is a risk of a first fault in the transmission line. As the wildfire approaches the first... The first power transmission corridor In a transmission line segment, increased conductor temperature causes a sharp drop in the dynamic rated current. When the difference between the dynamic rated current and the actual current is less than a preset current threshold, it is confirmed that the dynamic rated current is approaching or below the actual current, indicating a risk of a first-order fault in the transmission line. For example: when the current threshold is greater than 0 and is a relatively small value, if the difference between the dynamic rated current and the actual current is less than this threshold, it is confirmed that the dynamic rated current is approaching the actual current; when the current threshold is 0, if the difference between the dynamic rated current and the actual current is less than this threshold, it is confirmed that the dynamic rated current is less than the actual current.

[0078] In this embodiment of the application, if there is a risk of a first fault in the transmission line, the first fault probability is determined using a first fault probability calculation formula. The first fault probability calculation formula is: in, In the first The time interval is the probability of the first fault caused by the dynamic rated current decay. The first shape parameter is the preset shape parameter for the transmission line. The second shape parameter is a preset parameter for the transmission line. , The shape coefficients can be fitted based on the historical operating data of the transmission line, and can be 8 and 15 respectively.

[0079] In this embodiment of the application, if the difference between the dynamic rated current and the actual current is less than the current threshold, it is considered that the dynamic rated current of the transmission line under the influence of wildfire is close to or less than the actual current, thus determining the risk of the transmission line having a first fault. In the case of the risk of the transmission line having a first fault, the probability of the transmission line having a first fault under the influence of wildfire is determined, thereby improving the accuracy of predicting the risk of damage to the transmission line by wildfire.

[0080] Step 104: Based on the first fault probability, carry out wildfire prevention and control on the transmission line.

[0081] In this embodiment of the application, according to the transmission line in the first The time interval is determined by the probability of the first fault caused by the dynamic rated current decay. Using the formula for calculating the first cumulative fault probability, the duration of the wildfire can be determined for the transmission line. The first cumulative failure probability within. The formula for calculating the first cumulative failure probability is: in, The first cumulative failure probability, It is the time step. This refers to the number of time steps, where i refers to the i-th time step.

[0082] In this embodiment of the application, a wildfire prevention and control strategy for the transmission line can be determined based on the first cumulative fault probability, and wildfire prevention and control can be carried out on the transmission line in accordance with the wildfire prevention and control strategy.

[0083] In this embodiment, to address the operational risks of wildfires to power transmission lines, the size and location information of the affected transmission lines are obtained. Based on these information, the thermal balance parameters of the transmission lines under wildfire influence are determined. Using these parameters and the current actual current of the transmission lines, the thermal balance relationship is established, realizing the coupling between the wildfire's thermal radiation field and the thermophysical processes of the transmission lines. Based on this thermal balance relationship, the dynamic rated current of the transmission lines under wildfire influence is determined, enabling a quantitative assessment of the current-carrying capacity of the transmission lines under wildfire influence. Based on the dynamic rated current and actual current of the transmission lines, the first probability of failure is determined, coupling the wildfire's thermal radiation field with the nonlinear degradation of the cable's thermophysical properties. This quantitatively characterizes the performance degradation path of cable materials under accumulated thermal stress, improving the accuracy of predicting the risk of damage to power transmission lines caused by wildfires. Based on the first failure probability of transmission lines under the influence of wildfires, wildfire prevention and control of transmission lines is carried out, realizing an adaptive mapping from failure probability to prevention and control measures, and improving the accuracy of wildfire prevention and control of transmission lines.

[0084] In some embodiments of this application, the wildfire prevention and control method further includes: Based on the initial temperature of the transmission line before the wildfire occurred and the current temperature of the transmission line under the influence of the wildfire, the temperature rise data of the transmission line under the influence of the wildfire is determined; Using the current temperature, the temperature rise data, and the preset tensile strength loss ratio parameter of the transmission line under the influence of the wildfire, the life loss parameter of the transmission line under the influence of the wildfire is determined; Using the aforementioned life loss parameters, the safe operating time of the transmission line under the influence of the wildfire is predicted; Based on the safe operating time and the preset target operating time of the transmission line, the second failure probability of the transmission line under the influence of the wildfire is determined; Wildfire prevention and control measures are implemented for the power transmission line based on the second fault probability and the first fault probability.

[0085] In this embodiment, wildfires not only affect the dynamic rated current of transmission lines, but the high temperatures of wildfires also accelerate the thermal aging (TA) process of cables, causing annealing of transmission conductors, reducing their tensile strength, and increasing the risk of line-to-line flashover due to cable sagging caused by heat, thereby jeopardizing the lifespan of the transmission lines. In this embodiment, it can also be determined that the high temperatures of wildfires accelerate the thermal aging of transmission lines, leading to a second probability of transmission line failure.

[0086] In this embodiment, a nonlinear life equation can be used to assess the risk of increased sag due to thermal aging. Specifically, the temperature rise data of the transmission line under the influence of a wildfire can be determined based on the initial temperature preset before the wildfire and the current temperature of the transmission line under the influence of the wildfire. Using the temperature rise data, the current temperature of the transmission line, and the preset tensile strength loss ratio parameter of the transmission line under the influence of wildfires, the life loss parameter of the transmission line under the influence of wildfires can be determined using a preset life loss function. The life loss function is: in, This refers to the lifetime loss parameter; Pre-defined parameters for the proportion of tensile strength loss of transmission lines under the influence of wildfires; This is due to the loss of strength during annealing; This represents the initial maximum tensile strength of the transmission line; it can be determined based on the conductor type of the transmission line. , , All are k-series parameters. The series parameters are the material constants of the conductors in the transmission line.

[0087] In this embodiment, by using the lifespan loss parameters of transmission lines and the calculation formula for safe operating time, the safe operating time that the transmission line can withstand after experiencing additional temperature rise from wildfires can be predicted. Safe operating time is also known as lifespan. The calculation formula for safe operating time is: in, For safe operating time, It is also a conductor material constant for power transmission lines.

[0088] In this embodiment, the second fault probability of the transmission line under the influence of wildfire can be determined based on the safe operating time and the preset target operating time of the transmission line, using a formula for calculating the second fault probability. The second fault probability is also known as the failure rate of physical flashover caused by thermal aging exceeding a threshold. If the transmission line is made of steel-cored aluminum stranded wire, the thermal aging threshold for steel-cored aluminum stranded wire can be 75 degrees Celsius. The formula for calculating the second fault probability is: in, In the first The probability of the second failure within the time interval, The calculation step size is set to the preset probability. For the target runtime, For safe operating time, The third shape parameter, which is a preset parameter for the transmission line, can be calibrated based on the material fatigue characteristics of the transmission line and can be set to 5. The target operating time can also be called the design operating cycle (if the design operating cycle is 30 years, then the operating period is 8760 hours per year, for a total of 262,800 hours).

[0089] In this embodiment of the application, according to the transmission line in the first The second fault probability of the time interval, calculated using the formula for the second cumulative fault probability, can determine the duration of the wildfire on the transmission line. The second cumulative failure probability within. The formula for calculating the second cumulative failure probability is: in, This represents the second cumulative failure probability.

[0090] In this embodiment, cellular automata can be used to simulate the nonlinear spread of wildfires during combustion, determine the wildfire edge location information at any time point during the combustion process, and then determine the first affected area by the wildfire. The first power transmission corridor The first and second cumulative fault probabilities of the transmission line section transform the "fire trajectory" on the environmental side into the "risk probability" on the power grid side.

[0091] For each complete power transmission corridor The calculation formula for the comprehensive failure probability of the first corridor level is adopted. The first cumulative failure probability and the second cumulative failure probability of all transmission lines included in the corridor are then calculated in series within time period T to obtain the comprehensive failure probability of the first corridor level. The calculation formula for the comprehensive failure probability of the first corridor level is as follows: in, The overall failure probability for the first corridor level. Let m be the number of power transmission lines in the m-th power transmission corridor.

[0092] In this embodiment of the application, a wildfire prevention and control strategy for the transmission line can be determined based on the comprehensive failure probability of the first corridor level, and wildfire prevention and control can be carried out on the transmission line in accordance with the wildfire prevention and control strategy.

[0093] In this embodiment, the current temperature, temperature rise data, and tensile strength loss ratio of the transmission line under the influence of wildfires are used to determine the lifespan loss parameters of the transmission line under the influence of wildfires. This quantifies the impact of the high temperature of wildfires accelerating the thermal aging process of cables. This thermal aging process significantly increases the risk of cable sagging due to heat, leading to wire contact flashover and thus endangering the lifespan of the transmission line. Using the lifespan loss parameters, the safe operating time of the transmission line under the influence of wildfires can be predicted. Based on this safe operating time and the preset target operating time of the line, the second failure probability of the transmission line under the influence of wildfires is determined. This scheme realizes the coupled analysis of the thermal radiation field of wildfires and the nonlinear decay of the thermophysical properties of cables, further improving the accuracy of predicting the risk of damage to transmission lines by wildfires. Based on the aforementioned first and second failure probabilities of the transmission line under the influence of wildfires, wildfire prevention and control measures are implemented for the transmission line, thereby further improving the accuracy of wildfire prevention and control.

[0094] In some embodiments of this application, the power transmission line is erected above combustible material; the wildfire is formed by the combustion of the combustible material; the power transmission line includes at least two parallel transmission conductors; the at least two parallel transmission conductors are located on the same plane parallel to the ground; the wildfire prevention and control method further includes: Determine the burning height data of the wildfire, the height difference between the power transmission line and the combustible material, and the distance between the at least two parallel power transmission lines; Based on the combustion height data, the height difference, and the distance between the power transmission lines, the breakdown probability of the power transmission line under the influence of the wildfire is determined; the breakdown probability includes a first breakdown probability between the power transmission lines and a second breakdown probability of the power transmission line relative to the ground; Based on the first breakdown probability and the second breakdown probability, a third fault probability of the transmission line under the influence of the wildfire is determined. Wildfire prevention and control measures are implemented for the power transmission line based on the third fault probability, the second fault probability, and the first fault probability.

[0095] In this embodiment, the power transmission line is erected above combustible materials, and wildfires are formed by the combustion of these materials, which may include vegetation. The power transmission line includes at least two parallel transmission conductors, which are located on the same plane parallel to the ground, meaning the transmission conductors are at the same height.

[0096] In this embodiment, wildfires are highly conductive, and the high temperatures and ash they produce significantly reduce air insulation performance, inducing insulation breakdown and tripping of transmission lines. Therefore, the probability of a third fault caused by insulation breakdown of transmission lines under the influence of wildfires can be calculated.

[0097] In this embodiment, the breakdown probability of a power transmission line under the influence of a wildfire can be determined based on data on the fire height of the wildfire, the height difference between the transmission line and the combustible material, and the distance between the transmission conductors. This breakdown probability can include a first breakdown probability of the air insulation between the transmission conductors being broken down and a second breakdown probability of the air insulation between the transmission line and the ground being broken down.

[0098] In this embodiment, based on the first breakdown probability and the second breakdown probability, the third fault probability of the transmission line under the influence of wildfire can be determined using the calculation formula for the third fault probability. The calculation formula for the third fault probability is: in, This represents the third failure probability. This represents the second probability of penetration. This represents the first breakdown probability.

[0099] In this embodiment of the application, for wildfires that have already burned to a distance of the first... The first power transmission corridor When the minimum distance of a transmission line segment is less than a preset threshold, the calculation formula for the comprehensive failure probability of the second corridor level can be used to obtain the comprehensive failure probability of the second corridor level. This preset threshold can be 1 kilometer. The calculation formula for the comprehensive failure probability of the second corridor level is as follows: in, This represents the overall failure probability at the second corridor level.

[0100] In this embodiment of the application, a wildfire prevention and control strategy for the transmission line can be determined based on the comprehensive failure probability of the second corridor level, and wildfire prevention and control can be carried out on the transmission line in accordance with the wildfire prevention and control strategy.

[0101] In this embodiment of the application, after obtaining the first corridor-level comprehensive failure probability or the second corridor-level comprehensive failure probability of any transmission line in any transmission corridor, a spatiotemporal vulnerability probability matrix of the power grid can be generated. The spatiotemporal vulnerability probability matrix of the power grid can be plotted with time as the horizontal axis and the line number of the transmission line as the vertical axis, including the failure probability of each transmission line in multiple future time periods.

[0102] In this embodiment of the application, based on the burning height data of wildfires, the height difference between power transmission lines and combustibles, and the distance between at least two parallel power transmission conductors, the breakdown probability of power transmission lines under the influence of wildfires is determined. The breakdown probability includes the first breakdown probability between power transmission conductors and the second breakdown probability of power transmission lines relative to the ground. This realizes the consideration of the electrical breakdown effect caused by wildfires at extremely close distances, that is, the flames themselves have high conductivity, and the high temperature and smoke containing a large amount of ash they generate will significantly reduce the air insulation performance between power transmission lines and the ground, as well as the air insulation performance between power transmission conductors.

[0103] In this embodiment, based on the first and second breakdown probabilities, the third fault probability of the transmission line under the influence of wildfire is determined. Based on the third fault probability, the second fault probability, and the first fault probability, the third wildfire prevention and control strategy for the transmission line is determined. This not only incorporates the dynamic rated current and cable thermal aging effect during the fire spread process into the fault probability assessment system, but also introduces the air insulation breakdown model caused by wildfire flames and high-temperature smoke. This achieves the accurate prediction of the fault probability of the transmission line in the rapidly evolving and highly complex extreme wildfire scenario by precisely quantifying the comprehensive tripping fault probability caused by the increase in line sag and the sharp decline in insulation performance under extreme high temperature environment.

[0104] In some embodiments of this application, determining the breakdown probability of the power transmission line under the influence of the wildfire based on the burning height data, the height difference, and the distance between the transmission conductors includes: Obtain the flame tolerance parameters of the transmission line to the wildfire, and determine the smoke tolerance parameters of the transmission line to the smoke from the wildfire. Determine whether the combustion height data is greater than the height difference value; If the combustion height data is greater than the height difference, then the breakdown probability of the power transmission line is determined by using the height difference, the distance between the power transmission conductors, and the flame tolerance parameter. If the combustion height data is less than the height difference, the breakdown probability of the transmission line is determined using the combustion height data, the height difference, the distance between the transmission conductors, the flame tolerance parameter, and the smoke tolerance parameter.

[0105] In this embodiment, the combustion height calculation formula can be used to calculate the combustion height data of a wildfire. The combustion height calculation formula is as follows: in, q represents the fire height data of the wildfire; q represents the fire line intensity; We represents the effective combustible load; v represents the ambient wind speed; θ represents the terrain slope angle; T represents the ambient temperature; F represents the wind speed; and H represents the altitude.

[0106] In this embodiment, the smoke tolerance parameter of the transmission line to wildfire smoke can be calculated using the formula for calculating the smoke tolerance parameter. The smoke tolerance parameter is also known as the average smoke tolerance field strength. The formula for calculating the smoke tolerance parameter is: in, I represents the flue gas tolerance parameter; I represents the flue gas concentration index. The ambient temperature; Altitude; This is the reference field strength for clean air.

[0107] In this embodiment of the application, the breakdown factor of the electrical insulation of the transmission line can be determined based on the burning height data of the wildfire and the height difference between the transmission line and the combustible material. If the burning height data is greater than the height difference, the breakdown factor is the wildfire; if the burning height data is less than the height difference, the breakdown factor is the wildfire and the smoke.

[0108] When the breakdown factor is wildfire, the burning height data H f Greater than the height difference d between the power transmission line and the combustible material l−t The withstand voltage U of the air gap between the transmission line and the ground g The withstand voltage U of the air gap between the power transmission line and the transmission line p The calculation formulas are as follows: in, This refers to the phase-to-phase distance between transmission lines; For flame withstand parameters, 35 kV / m (kilovolt per meter) can be taken.

[0109] When the breakdown factors are wildfire and smoke, the combustion height data H f Less than the height difference d between the power transmission line and the combustible material l−t The withstand voltage U of the air gap between the transmission line and the ground g The withstand voltage U of the air gap between the power transmission line and the transmission line p The calculation formulas are as follows: U P =d p E S In this embodiment, the combustion height data H can be calculated using the calculation formulas for the first breakdown probability and the second breakdown probability. fGreater than or less than the height difference d between the power transmission line and the combustible material l−t The probability of first breakdown and the probability of second breakdown in two cases. Wherein, the probability of first breakdown... The calculation formula is: Second penetration probability The calculation formula is: Where x is the integration variable, U N This is the system's nominal voltage.

[0110] In this embodiment, based on different breakdown factors, different methods for determining the breakdown probability are used, including wildfire combustion height data, the height difference between the transmission line and the combustible material, the distance between transmission conductors, and the flame and smoke tolerance parameters of the transmission line. This improves the accuracy of breakdown probability prediction. Based on the first and second breakdown probabilities of the transmission line, a third fault probability of the transmission line under the influence of wildfire is determined, achieving accurate prediction of the line tripping failure rate.

[0111] In some embodiments of this application, the step of controlling wildfires on the transmission line based on the third fault probability, the second fault probability, and the first fault probability includes: Based on the third fault probability, the second fault probability, and the first fault probability, the target fault probability of the transmission line under the influence of the wildfire is determined. Obtain the power supply information of the transmission line to the preset electrical equipment; The target failure probability, the spread information of the wildfire during the burning process, and the power supply information are input into a preset wildfire prevention and control model to obtain a wildfire prevention and control strategy. According to the aforementioned wildfire prevention and control strategy, wildfire prevention and control measures are implemented on the power transmission lines.

[0112] In this embodiment of the application, the power supply information of the transmission line to the preset electrical equipment can be obtained. Furthermore, the second corridor-level comprehensive failure probability of the transmission line under the influence of wildfire can be determined based on the third failure probability, the second failure probability, and the first failure probability, and the second corridor-level comprehensive failure probability can be used as the target failure probability.

[0113] In this embodiment, the target fault probability, power supply information, and wildfire spread information during combustion can be input into the wildfire prevention and control model to obtain the wildfire prevention and control strategy for the transmission line. Wildfire prevention and control measures can then be implemented on the transmission line according to this strategy. Alternatively, in this embodiment, the first fault probability or the first corridor-level comprehensive failure probability can be used as the target fault probability. The subsequent processing steps are the same as described above and will not be repeated here.

[0114] In a specific example, the information input into the wildfire prevention and control model includes the comprehensive failure probability matrix of each power grid segment. The probability matrix of future wildfire spatiotemporal evolution reflects the time and intensity distribution of fires reaching critical corridors; the current power grid topology, load demand of each node, and real-time branch power flow distribution, etc.

[0115] In this embodiment, the target failure probability of the transmission line under the influence of wildfire is determined based on the third failure probability, the second failure probability, and the first failure probability of the transmission line; the power supply information of the transmission line to the preset electrical equipment is obtained; the target failure probability, the spread information of the wildfire during the combustion process, and the power supply information are input into the preset wildfire prevention and control model to obtain the wildfire prevention and control strategy. This realizes the comprehensive consideration of the dynamic rated current during the fire spread process, the thermal aging effect of the cable, and the air insulation breakdown of the transmission line caused by the wildfire flames and high-temperature smoke, and determines the wildfire prevention and control strategy of the transmission line, thus achieving precise wildfire prevention and control.

[0116] In some embodiments of this application, the wildfire prevention and control method further includes: The training target failure probability of the transmission line under the influence of a preset training wildfire is obtained, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line for the training wildfire. The wildfire prevention and control model is obtained by training a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy.

[0117] In this embodiment, under three scenarios—using the first fault probability, the first corridor-level comprehensive failure probability, and the second corridor-level comprehensive failure probability as the target fault probability—the training target fault probability of the transmission line under the influence of a preset training wildfire, the training power supply information of the transmission line, the training spread information of the training wildfire during its combustion process, and the training prevention and control strategy of the transmission line against the training wildfire can all be obtained. Then, using the training target fault probability of the transmission line under the influence of the training wildfire, the training power supply information of the transmission line, the training spread information of the training wildfire during its combustion process, and the training prevention and control strategy of the transmission line against the training wildfire, the initial neural network model is trained, thereby constructing a wildfire prevention and control model to intelligently output prevention and control strategies for transmission lines under wildfire disasters.

[0118] In some embodiments of this application, the step of training a preset initial neural network model using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain the wildfire prevention and control model includes: The initial neural network model is updated using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain an updated neural network model. The updated neural network model is determined to output an inference and prevention strategy for the training wildfire based on the training target failure probability, the training power supply information, and the training spread information; the inference and prevention strategy includes cutting off the power supply to the transmission line or maintaining the power supply to the transmission line. Determine the fire risk cost of maintaining power supply to the transmission line according to the aforementioned reasoning and prevention strategy; Determine the load loss cost under the condition that the power supply to the transmission line is cut off according to the aforementioned reasoning and prevention strategy; Based on the fire risk cost and the load loss cost, determine the initial evaluation score of the reasoning prevention and control strategy, and based on the initial evaluation score, determine whether the updated neural network model meets the preset model training objective; If the updated neural network model satisfies the model training objective, then the updated neural network model will be used as the wildfire prevention and control model.

[0119] In this embodiment of the application, in order to achieve a balance between disaster prevention safety and power supply economy, the process of updating the initial neural network model involves two parts: load loss cost penalty and catastrophic risk cost penalty.

[0120] Load loss cost penalty refers to the total load reduction of the power grid system caused by active power outages or faults in transmission lines. During wildfire combustion... At any given time, the cost penalty for load loss caused by active defense or line faults in transmission lines. It can be defined as: in, exist At time i, the amount of active load lost due to active disconnection of power supply or fault at the i-th node, expressed in MW (megawatts). The unload value of the transmission line at the i-th node can be differentiated based on the number of terminal loads corresponding to that line.

[0121] The catastrophic risk cost penalty refers to the expected reconstruction costs of power transmission lines destroyed by fire, and the risk costs of third-party liability arising from secondary fires caused by these transmission lines. This is a severe penalty, forcing the model during training to prioritize defensive power outages rather than reckless operation when faced with a very high probability of failure. This is relevant during wildfires. At any moment, the catastrophic risk and penalty of power transmission lines exposed to wildfires It can be defined as: in, For the first The cost of physical replacement and emergency repair of a power transmission line after it has been completely burned out; Estimated costs for third-party liability insurance payouts in the event of secondary disasters caused by energized transmission lines; Let be the target failure probability at time t; For the action variable results output by the model during the training process, if This indicates that the transmission line remains energized. This indicates that the power transmission line has been actively disconnected.

[0122] During model training, the initial neural network model can be updated using training target failure probability, training power supply information, training spread information, and training prevention and control strategies to obtain an updated neural network model. Then, the updated neural network model outputs an inferred prevention and control strategy for the training wildfire based on the training target failure probability, training power supply information, and training spread information. This inferred prevention and control strategy includes either cutting off power to transmission lines or maintaining power supply to transmission lines. Next, the fire risk cost under the condition of maintaining power supply to transmission lines according to the inferred prevention and control strategy and the load loss cost under the condition of cutting off power supply to transmission lines according to the inferred prevention and control strategy can be determined. The fire risk cost is the same as the catastrophic risk cost.

[0123] In this embodiment of the application, the comprehensive reward value can be calculated based on the fire risk cost and the load loss cost using the comprehensive reward value calculation formula.

[0124] in, and This is a weighting coefficient used to adjust the bias between "ensuring power supply" and "avoiding major disasters"; This is the total reward value.

[0125] In this embodiment, a comprehensive reward value can be used, along with the formula for calculating the initial evaluation score, to determine the initial evaluation score of the inference prevention and control strategy. If the initial evaluation score is greater than a preset score threshold, it is confirmed that the updated neural network model meets the model training objective, and the updated application network model is used as the wildfire prevention and control model.

[0126] To prevent the model from getting stuck in local optima during the early stages of training, a policy entropy term can be introduced into the formula for calculating the initial evaluation score. This maximizes both cumulative rewards and the randomness of the strategy. The formula for calculating the initial evaluation score can be: in, This is the initial assessment score; Represents the mathematical expectation; Indicating in strategy Under control, the state of the power grid system and reasoning prevention strategies The resulting temporal trajectory distribution; In order to be in At what time, the state of the power grid system Execution reasoning and control strategy The immediate environmental feedback obtained, i.e., the overall reward value; This is a coefficient used to dynamically adjust the balance between exploration and utilization; Entropy, in information theory, measures the "uncertainty" or "diversity" of a probability distribution. Entropy is maximum when the model has the same preference for all actions; it is zero when the model is 100% certain of choosing only one action.

[0127] In a specific example, considering the characteristics of dynamic control of the power grid involving continuous-discrete mixed actions and stringent safety constraints across multiple time periods, a safety soft-action evaluation algorithm is adopted as the underlying architecture of the wildfire prevention and control model. This architecture is based on a constrained Markov decision process, and its specific algorithm framework and network structure are as follows: The wildfire prevention and control model includes a policy network. and value network Two core deep neural networks work together to complete "state awareness" and "action output": Policy Network : with parameters As weights, its input layer receives a comprehensive state vector containing the spatiotemporal vulnerability matrix. The output layer generates corresponding control actions. The network uses a Gaussian probability distribution and is responsible for "formulating control strategies" based on the current fire risk.

[0128] Value Network : with parameters The weights are the transmission line states of the power grid, and the input is the state of the power grid's transmission lines. With regulatory actions The concatenated vector is output as the expected cumulative reward value for performing the action in this state. To overcome the overestimation problem of traditional algorithms, a dual-Critic network structure is preferably adopted. , The minimum value is used for value assessment.

[0129] In this embodiment, when determining whether the updated neural network model meets the model training objective, the fire risk cost and load loss cost of the inference prevention and control strategy output by the updated neural network model are comprehensively considered to determine the initial evaluation score of the inference prevention and control strategy, and to determine whether the updated neural network model meets the model training objective. This allows the trained wildfire prevention and control model to comprehensively consider the fire risk cost and load loss cost, and output the transmission line's wildfire prevention and control strategy. This solves the problem in related technologies where, when the risk level of a wildfire to the normal operation of a specific transmission line of the power grid exceeds the safety threshold, directly cutting off the power transmission of that line often leads to over-defense against wildfire risks, causing large-scale and long-term unnecessary power outages and resulting in huge socio-economic losses.

[0130] In this embodiment, the target failure probability of the transmission line under the influence of wildfire, the spread information of the wildfire during the burning process, and the power supply information of the transmission line to the electrical equipment are input into the wildfire prevention and control model to obtain the wildfire prevention and control strategy of the transmission line. This realizes that the wildfire prevention and control strategy can be changed according to the spread information of the wildfire during the burning process. At the same time, based on the predicted time and intensity probability of the fire reaching the transmission line, the optimal balance path is found between "maximizing the continuous power supply" and "minimizing the risk of equipment burnout and secondary disasters" in multiple time periods. Thus, the disaster prevention strategy is upgraded from static passive response to forward-looking dynamic control, which solves the problem that the existing wildfire defense methods are too crude and lack multi-time period refined decision-making based on high-precision spatiotemporal extrapolation.

[0131] In some embodiments of this application, determining whether the updated neural network model meets the preset model training objective based on the initial evaluation score includes: When the training wildfire is controlled according to the aforementioned reasoning and control strategy, the inference current of the transmission line is determined. If the inference current is not less than the dynamic rated current, then the initial evaluation score is reduced by using a preset safety cost function to obtain the target evaluation score; If the target evaluation score is not less than the preset evaluation score threshold, then the updated neural network model is confirmed to meet the model training objective.

[0132] In this embodiment, the wildfire prevention and control model has safety constraints. These safety constraints mean that the prevention and control strategy output by the wildfire prevention and control model can ensure that the current in the transmission lines is less than the dynamic rated current when wildfires are controlled.

[0133] To ensure that the wildfire prevention and control strategy has safety constraints, during the model training process, the inference current of the transmission line can be determined when training wildfire prevention and control according to the inference prevention and control strategy. The inference current refers to the current flowing through the transmission line when training wildfire prevention and control according to the inference prevention and control strategy.

[0134] If the inference current is not less than the dynamic rated current, then a preset safety cost function is used to reduce the initial evaluation score, thus obtaining the target evaluation score. Specifically, the Lagrange multiplier method can be used, defining the safety cost function for violating the physical safety boundary (i.e., the inference current is not less than the dynamic rated current) as follows: By setting a safety threshold of d, the constrained optimization problem is transformed into an unconstrained Lagrangian dual problem: in, These are learnable Lagrange multipliers, i.e., safety penalty weights; These are the trainable parameters of the model; For reasoning and prevention strategies Initial assessment score; For expectation operators; This is the discount factor.

[0135] When updating the network gradient of the model through backpropagation, once the model outputs the inference prevention strategy... During execution, the inference current of the transmission line shall not be less than the dynamic rated current. The value will rapidly and automatically surge, generating a huge penalty gradient, forcing the model's inference and defense strategies to quickly move away from the dangerous action space.

[0136] In this embodiment of the application, if the target evaluation score after the initial evaluation score is reduced is not less than the preset evaluation score threshold, then it is confirmed that the updated neural network model meets the model training objective.

[0137] In this embodiment, due to the inherent probabilistic uncertainty of the wildfire prevention and control model, a physical verification layer is connected in series before the wildfire prevention and control strategy output by the model is sent to the physical layer. If the physical verification layer detects that the execution of the wildfire prevention and control strategy will cause the power flow of the transmission line to exceed the DTR threshold of real-time attenuation, a safety interception is triggered, and a fallback protection rule of heuristic power outage or voltage reduction is forcibly executed, thereby ensuring the absolute physical safety boundary and guaranteeing that the current of the transmission line is less than the dynamic rated current.

[0138] In this embodiment, when training wildfire prevention and control strategies according to the inference prevention and control strategies output by the updated neural network model, the inference current of the transmission line is determined. Under the condition that the inference current is not less than the dynamic rated current, the initial evaluation score is reduced by using a safety cost function to obtain the target evaluation score of the inference prevention and control strategy. The model is optimized based on the target evaluation score. This achieves the goal that, during the model training process, the prevention and control strategy output by the wildfire prevention and control model can ensure that the current of the transmission line is less than the dynamic rated current when controlling wildfires, so as to ensure the safe operation of the transmission line under the influence of wildfires.

[0139] In this embodiment, under three scenarios where the first fault probability, the first corridor-level comprehensive failure probability, and the second corridor-level comprehensive failure probability are used as the target fault probability, the wildfire prevention and control strategy output by the wildfire prevention and control model can include: a preventive shutdown schedule for the main power grid and supporting reference values ​​for distributed energy resources on the distribution side. The main power grid refers to the transmission lines affected by wildfires, and the distributed energy resources on the distribution side refer to the backup power supply equipment for these transmission lines. The wildfire prevention and control strategy can include the power shutdown time of the transmission lines to the electrical equipment and the power supply information of the backup power supply equipment of the transmission lines to the electrical equipment. The power shutdown time can be different for different transmission lines.

[0140] In this embodiment of the application, before the power supply cut-off time, a power supply command is sent to the backup power supply equipment according to the power supply information of the backup power supply equipment, so that the backup power supply equipment supplies power to the electrical equipment in place of the transmission line; during the power supply cut-off time, the power supply of the transmission line is cut off.

[0141] In this embodiment, before the power supply to the transmission line is cut off, a power supply command is sent to the backup power supply equipment of the transmission line, so that the backup power supply equipment supplies power to the electrical equipment in place of the transmission line. At the power supply cutoff time, the power supply to the transmission line is cut off. This realizes that the backup power supply equipment of the transmission line starts supplying power to the transmission line before the power supply to the electrical equipment is cut off. This solves the problem that the related technology lacks a full-process coordinated control mechanism between the transmission and distribution networks. It focuses on the post-disaster recovery technology of the distribution network side after a disaster occurs and causes the main network to lose power, which limits the power supply level of the power system to electrical equipment in the face of extreme natural disasters.

[0142] In a specific example, the steps for issuing a wildfire prevention and control strategy and controlling the main power grid and distributed energy resources on the distribution side according to the strategy are as follows: I. Backbone Network Front-End Physical Isolation (1) Command conversion and distribution: The power grid energy management system converts the virtual power outage command into a specific control message and distributes it to the smart terminals and circuit breakers on both sides of the target line.

[0143] (2) Active defense action: Before the heat radiation from the wildfire causes flashover of the conductor or triggers a secondary fire, the circuit breaker will trip to disconnect the faulty line. At the same time, the system will use topology analysis to identify whether electrical islands have been formed in the power grid due to the disconnection. If an island is formed, subsequent steady-state analysis and control will be performed independently for each island.

[0144] II. Transmission and Distribution Coordination Triggering Mechanism (1) During the same control cycle when the main grid circuit breaker executes the trip command (or 1 to 2 control cycles in advance), the EMS (Energy Management System) master station uses the high-speed communication network to simultaneously send the "main grid power failure warning" and "island network formation command" to the microgrid central controller of the affected distribution area.

[0145] (2) Ensure that the distribution network side completes the takeover preparation before the main grid voltage actually drops, so as to avoid the voltage and frequency inside the distribution network from drastic fluctuations due to sudden power outages.

[0146] III. Distribution Network Takeover and Microgrid Self-Healing Control When the microgrid central controller receives the islanding command, it immediately activates the distributed flexibility resources in the distribution network to provide self-healing support.

[0147] (1) Seamless switching of control modes: Distributed energy inverters and energy storage systems in the region can quickly switch from grid-connected follower mode (PQ control) to islanded grid mode. It is preferred to use master-slave control (with large-capacity energy storage as the main power source to provide voltage and frequency reference) or peer-to-peer droop control to maintain voltage and frequency stability within the microgrid.

[0148] (2) Load shedding and supply guarantee based on AC-OPF: Under the framework set by the reinforcement learning agent (used to output macroscopic support reference values ​​on the distribution side), if the total available capacity of distributed energy in the island is temporarily unable to support all loads, the microgrid central controller triggers the execution of the deterministic AC optimal power flow (AC-OPF) subroutine. This subroutine calculates the minimum load reduction required to maintain system stability based on the preset load priority list, and prioritizes the protection of first-level critical loads such as hospitals and fire stations.

[0149] In this embodiment, compared to related technologies where risk assessments often separate the external spread of fire from the physical and electrical degradation of power grid equipment, this embodiment constructs a dynamic spatiotemporal vulnerability model that deeply couples thermodynamic deformation and electrical insulation failure. This model not only integrates fire thermal radiation with the nonlinear decay of dynamic thermal rating (DTR) and the cumulative effect of thermal aging (TA) within transmission lines, but also innovatively introduces a model for air gap breakdown caused by wildfire flames and high-temperature smoke. By quantifying with high precision the combined tripping probability caused by extreme high temperatures leading to "conductor sag falling below safe distance" and "a sharp decline in air insulation performance," this method completely eliminates the blind spot of traditional static models' insufficient estimation of the system's true disaster resistance capability. This provides a decision-making benchmark that most closely reflects the real multiphysics evolution for subsequent proactive defense.

[0150] This application completely breaks away from the traditional "one-size-fits-all" approach of proactive power outage strategies, achieving an optimal balance between disaster prevention economy and safety. Addressing the shortcomings of traditional preventative proactive power outages in related technologies, such as lack of dynamic simulation and the potential for over-defense and huge socio-economic losses, this application achieves a leap from passive static response to proactive dynamic control. Based on a high-fidelity spatiotemporal vulnerability matrix and cellular automata fire simulation, "catastrophic risk costs" and "economic costs of load reduction" are jointly incorporated into the reward and punishment evaluation system. This enables the system to accurately decide "when, where, and how much load to cut off" during rapid online optimization, maximizing the continuous power supply of the entire system under the absolute safety constraints of ensuring no secondary fires and no equipment damage.

[0151] In related technologies, the emergency power outage of the backbone network and the post-disaster recovery of the distribution network typically operate independently. When the backbone network is forced to implement preventative disconnection due to disaster prevention needs, the flexible resources of the distribution network (such as distributed energy and energy storage) cannot intervene in advance based on the global disaster evolution status. This lack of a "backbone network pre-isolation - distribution network early response" disconnection prevents the distribution network from achieving a smooth "self-healing" proactive response, greatly limiting the survivability and power supply level of new power systems in the face of extreme natural disasters, and easily leading to power supply chain breaks. The embodiments of this application establish a cross-level transmission and distribution coordination second-level self-healing mechanism. Under the coordination of a security reinforcement learning agent, the system can simultaneously (or in advance) issue the islanding network formation command to the distributed energy and energy storage devices in the affected distribution area while the backbone network issues the preventative disconnection command. This combined action of "preemptive cut-off of the main grid to block cascading disasters and early response of the distribution network to smoothly take over the load" enables the power grid to protect core backbone equipment and achieve seamless self-healing on the distribution network side when facing the impact of extreme wildfires, fundamentally improving the overall disaster resistance resilience of the power system.

[0152] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments of this application are not limited to the described order of actions, because according to the embodiments of this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of this application.

[0153] Reference Figure 2 This application also discloses a structural block diagram of a wildfire prevention device for power transmission lines, applied to power transmission lines. The wildfire prevention device includes: The acquisition module 201 is used to acquire the size information and location information of the power transmission lines under the influence of wildfires. The thermal balance relationship determination module 202 is used to determine the thermal balance parameters of the transmission line under the influence of the wildfire based on the size information, the line location information and the wildfire information, and to determine the thermal balance relationship of the transmission line under the influence of the wildfire using the thermal balance parameters and the current actual current of the transmission line. The first fault probability determination module 203 is used to determine the dynamic rated current of the transmission line under the influence of the wildfire based on the thermal balance relationship, and to determine the first fault probability of the transmission line based on the dynamic rated current and the actual current. The first wildfire prevention module 204 is used to prevent wildfires from spreading on the transmission line based on the first fault probability.

[0154] In one optional embodiment of this application, the wildfire information includes fire source location information and environmental information surrounding the fire source; the heat balance parameter includes the heat transferred from the wildfire to the transmission line; the heat balance relationship determination module includes: The wildfire edge location information determination submodule is used to determine the spread information of the wildfire during the combustion process based on the fire source location information and the environmental information, and to determine the wildfire edge location information at any time point during the combustion process based on the spread information; The heat flux determination submodule is used to determine the heat flux transmitted from the wildfire to the transmission line based on the line location information and the wildfire edge location information; The heat determination submodule is used to determine the heat transferred from the wildfire to the power transmission line based on the heat flux and the size information.

[0155] In one optional embodiment of this application, the heat balance parameters further include the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat of the transmission line under solar irradiation, and the current temperature of the transmission line under the influence of the wildfire; the heat balance relationship determination module includes: A resistance determination submodule is used to determine the resistance of the transmission line at the current temperature based on the current temperature. The thermal balance relationship determination submodule is used to determine the thermal balance relationship of the transmission line under the influence of the wildfire by using the resistance, the convective heat loss rate, the radiative heat loss rate, the solar radiation heat, the heat transferred from the wildfire to the transmission line, and the actual current.

[0156] In one optional embodiment of this application, the first fault probability determination module includes: The current threshold determination submodule is used to determine whether the difference between the dynamic rated current and the actual current is less than a preset current threshold. The first fault probability determination submodule is used to determine the first fault probability of the transmission line based on the preset shape parameters of the transmission line, the dynamic rated current, and the actual current if the difference between the dynamic rated current and the actual current is less than the current threshold.

[0157] In one optional embodiment of this application, the wildfire prevention and control device further includes: The temperature rise data determination module is used to determine the temperature rise data of the transmission line under the influence of the wildfire based on the preset initial temperature of the transmission line before the wildfire occurred and the current temperature of the transmission line under the influence of the wildfire. The lifespan loss parameter determination module is used to determine the lifespan loss parameters of the transmission line under the influence of the wildfire by using the current temperature, the temperature rise data and the tensile strength loss ratio parameter preset by the transmission line under the influence of the wildfire. The safe operating time prediction module is used to predict the safe operating time of the transmission line under the influence of the wildfire using the life loss parameters. The second fault probability determination module is used to determine the second fault probability of the transmission line under the influence of the wildfire based on the safe operating time and the preset target operating time of the transmission line. The second wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the second fault probability and the first fault probability.

[0158] In one optional embodiment of this application, the power transmission line is erected above the combustible material; the wildfire is formed by the combustion of the combustible material; the power transmission line includes at least two parallel transmission conductors; the at least two parallel transmission conductors are located on the same plane parallel to the ground; the wildfire prevention device further includes: The distance determination module is used to determine the burning height data of the wildfire, the height difference between the power transmission line and the combustible material, and the distance between the at least two parallel power transmission lines; A breakdown probability determination module is used to determine the breakdown probability of the power transmission line under the influence of the wildfire based on the burning height data, the height difference, and the distance between the power transmission conductors; the breakdown probability includes a first breakdown probability between the power transmission conductors and a second breakdown probability of the power transmission line relative to the ground; The third fault probability determination module is used to determine the third fault probability of the transmission line under the influence of the wildfire based on the first breakdown probability and the second breakdown probability. The third wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the third fault probability, the second fault probability, and the first fault probability.

[0159] In one optional embodiment of this application, the breakdown probability determination module includes: The tolerance parameter acquisition submodule is used to acquire the flame tolerance parameters of the transmission line to the wildfire and determine the smoke tolerance parameters of the transmission line to the smoke from the wildfire. The height determination submodule is used to determine whether the combustion height data is greater than the height difference value; The first breakdown probability determination submodule is used to determine the breakdown probability of the power transmission line by using the height difference, the distance between the power transmission conductors, and the flame tolerance parameter if the combustion height data is greater than the height difference. The second breakdown probability determination submodule is used to determine the breakdown probability of the transmission line by using the combustion height data, the height difference, the distance between the transmission conductors, the flame tolerance parameter, and the smoke tolerance parameter if the combustion height data is less than the height difference value.

[0160] In one optional embodiment of this application, the third wildfire prevention module includes: The target failure probability determination submodule is used to determine the target failure probability of the transmission line under the influence of the wildfire based on the third failure probability, the second failure probability and the first failure probability. The power supply information acquisition submodule is used to acquire the power supply information of the transmission line to the preset electrical equipment; The strategy acquisition submodule is used to input the target failure probability, the spread information of the wildfire during the combustion process, and the power supply information into a preset wildfire prevention and control model to obtain a wildfire prevention and control strategy; The wildfire prevention and control submodule is used to carry out wildfire prevention and control on the transmission line according to the wildfire prevention and control strategy.

[0161] In one optional embodiment of this application, the wildfire prevention and control device further includes: The training information acquisition submodule is used to acquire the training target failure probability of the transmission line under the influence of a preset training wildfire, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line for the training wildfire. The training submodule is used to train a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy to obtain the wildfire prevention and control model.

[0162] In one optional embodiment of this application, the training submodule includes: The update unit is used to update the initial neural network model using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain an updated neural network model. An inference strategy output unit is used to determine the inference prevention and control strategy for the training wildfire output by the updated neural network model based on the training target fault probability, the training power supply information, and the training spread information; the inference prevention and control strategy includes cutting off the power supply to the transmission line or maintaining the power supply to the transmission line; A fire risk cost determination unit is used to determine the fire risk cost of maintaining the power supply of the transmission line in accordance with the reasoning and prevention strategy. A load loss cost determination unit is used to determine the load loss cost under the condition that the power supply to the transmission line is cut off according to the reasoning and prevention strategy; The initial evaluation score determination unit is used to determine the initial evaluation score of the reasoning prevention and control strategy based on the fire risk cost and the load loss cost, and to determine whether the updated neural network model meets the preset model training objective based on the initial evaluation score. The model is used as a unit to take the updated neural network model as the wildfire prevention and control model if the updated neural network model meets the model training objective.

[0163] In one optional embodiment of this application, the initial evaluation score determination unit includes: The inference current determination subunit is used to determine the inference current of the transmission line when the training wildfire is controlled according to the inference control strategy. The target evaluation score is obtained by sub-units, which are used to reduce the initial evaluation score by using a preset safety cost function if the inference current is not less than the dynamic rated current, so as to obtain the target evaluation score. The model training objective confirmation subunit is used to confirm that the updated neural network model meets the model training objective if the objective evaluation score is not less than a preset evaluation score threshold.

[0164] It is understood that the above-described device embodiments correspond to the method embodiments of this application, and can implement the method provided by any of the above-described method embodiments of this application.

[0165] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided in this application, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0166] Based on the embodiments of the above methods, another embodiment of this application provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the method described in any embodiment of this application.

[0167] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete this application. The one or more module units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0168] The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0169] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0170] Based on the above-described method embodiments, another embodiment of this application provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the method described in any of the above-described method embodiments of this application.

[0171] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0172] Based on the above-described method embodiments, another embodiment of this application provides a computer program product, including a computer program or instructions, which, when executed by a communication device, implements the method described in any of the above-described method embodiments of this application.

[0173] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of this application. It should be understood that the above descriptions are merely specific embodiments of this application and are not intended to limit the scope of protection of this application. In particular, it should be noted that any modifications, equivalent substitutions, or improvements made by those skilled in the art within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for preventing wildfires along power transmission lines, characterized in that, The wildfire prevention and control method, applied to power transmission lines, includes: Obtain the size and location information of power transmission lines affected by wildfires; Based on the size information, the line location information, and the wildfire information, the heat balance parameters of the transmission line under the influence of the wildfire are determined, and the heat balance parameters and the current actual current of the transmission line are used to determine the heat balance relationship of the transmission line under the influence of the wildfire. Based on the aforementioned thermal balance relationship, the dynamic rated current of the transmission line under the influence of the wildfire is determined, and based on the dynamic rated current and the actual current, the first fault probability of the transmission line is determined. Based on the first fault probability, wildfire prevention and control measures are implemented for the power transmission line.

2. The method for preventing wildfires along power transmission lines according to claim 1, characterized in that, The wildfire information includes fire source location information and environmental information surrounding the fire source; the heat balance parameters include the heat transferred from the wildfire to the transmission line; determining the heat balance parameters of the transmission line under the influence of the wildfire based on the size information, the line location information, and the wildfire information includes: Based on the fire source location information and the environmental information, the spread information of the wildfire during the burning process is determined, and based on the spread information, the edge location information of the wildfire at any time point during the burning process is determined; Based on the line location information and the wildfire edge location information, the heat flux from the wildfire to the transmission line is determined; Based on the heat flux and the size information, the amount of heat transferred from the wildfire to the power transmission line is determined.

3. The method for preventing wildfires along power transmission lines according to claim 2, characterized in that, The heat balance parameters also include the convective heat loss rate of the transmission line, the radiative heat loss rate of the transmission line, the solar radiation heat of the transmission line under solar irradiation, and the current temperature of the transmission line under the influence of the wildfire. The process of determining the heat balance relationship of the transmission line under the influence of the wildfire by using the heat balance parameters and the current actual current of the transmission line includes: Based on the current temperature, determine the resistance of the transmission line at the current temperature; The thermal balance relationship of the transmission line under the influence of the wildfire is determined by using the resistance, the convective heat loss rate, the radiative heat loss rate, the solar radiation heat, the heat transferred from the wildfire to the transmission line, and the actual current.

4. The method for preventing wildfires along power transmission lines according to claim 1, characterized in that, Determining the first fault probability of the transmission line based on the dynamic rated current and the actual current includes: Determine whether the difference between the dynamic rated current and the actual current is less than a preset current threshold. If the difference between the dynamic rated current and the actual current is less than the current threshold, then the first fault probability of the transmission line is determined based on the preset shape parameters of the transmission line, the dynamic rated current, and the actual current.

5. The method for preventing wildfires along power transmission lines according to claim 3, characterized in that, The methods for preventing and controlling wildfires also include: Based on the initial temperature of the transmission line before the wildfire occurred and the current temperature of the transmission line under the influence of the wildfire, the temperature rise data of the transmission line under the influence of the wildfire is determined; Using the current temperature, the temperature rise data, and the preset tensile strength loss ratio parameter of the transmission line under the influence of the wildfire, the life loss parameter of the transmission line under the influence of the wildfire is determined; Using the aforementioned life loss parameters, the safe operating time of the transmission line under the influence of the wildfire is predicted; Based on the safe operating time and the preset target operating time of the transmission line, the second failure probability of the transmission line under the influence of the wildfire is determined; Wildfire prevention and control measures are implemented for the power transmission line based on the second fault probability and the first fault probability.

6. The method for preventing wildfires along power transmission lines according to claim 5, characterized in that, The power transmission line is erected above combustible material; the wildfire is formed by the combustion of the combustible material; the power transmission line includes at least two parallel transmission conductors; the at least two parallel transmission conductors are located on the same plane parallel to the ground; the wildfire prevention and control method further includes: Determine the burning height data of the wildfire, the height difference between the power transmission line and the combustible material, and the distance between the at least two parallel power transmission lines; Based on the combustion height data, the height difference, and the distance between the power transmission lines, the breakdown probability of the power transmission line under the influence of the wildfire is determined; the breakdown probability includes a first breakdown probability between the power transmission lines and a second breakdown probability of the power transmission line relative to the ground; Based on the first breakdown probability and the second breakdown probability, a third fault probability of the transmission line under the influence of the wildfire is determined. Wildfire prevention and control measures are implemented for the power transmission line based on the third fault probability, the second fault probability, and the first fault probability.

7. The method for preventing wildfires along power transmission lines according to claim 6, characterized in that, The determination of the breakdown probability of the power transmission line under the influence of the wildfire, based on the combustion height data, the height difference, and the distance between the power transmission lines, includes: Obtain the flame tolerance parameters of the transmission line to the wildfire, and determine the smoke tolerance parameters of the transmission line to the smoke from the wildfire. Determine whether the combustion height data is greater than the height difference value; If the combustion height data is greater than the height difference, then the breakdown probability of the power transmission line is determined by using the height difference, the distance between the power transmission conductors, and the flame tolerance parameter. If the combustion height data is less than the height difference, the breakdown probability of the transmission line is determined using the combustion height data, the height difference, the distance between the transmission conductors, the flame tolerance parameter, and the smoke tolerance parameter.

8. The method for preventing wildfires along transmission lines according to claim 6, characterized in that, The method of controlling wildfires on the transmission line based on the third fault probability, the second fault probability, and the first fault probability includes: Based on the third fault probability, the second fault probability, and the first fault probability, the target fault probability of the transmission line under the influence of the wildfire is determined. Obtain the power supply information of the transmission line to the preset electrical equipment; The target failure probability, the spread information of the wildfire during the burning process, and the power supply information are input into a preset wildfire prevention and control model to obtain a wildfire prevention and control strategy. According to the aforementioned wildfire prevention and control strategy, wildfire prevention and control measures are implemented on the power transmission lines.

9. The method for preventing wildfires along power transmission lines according to claim 8, characterized in that, The methods for preventing and controlling wildfires also include: The training target failure probability of the transmission line under the influence of a preset training wildfire is obtained, the training power supply information of the transmission line, the training spread information of the training wildfire during the burning process, and the training prevention and control strategy of the transmission line for the training wildfire. The wildfire prevention and control model is obtained by training a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy.

10. The method for preventing wildfires along transmission lines according to claim 9, characterized in that, The method of training a preset initial neural network model using the training target fault probability, the training power supply information, the training spread information, and the training prevention and control strategy to obtain the wildfire prevention and control model includes: The initial neural network model is updated using the training target fault probability, the training power supply information, the training propagation information, and the training prevention and control strategy to obtain an updated neural network model. The updated neural network model is determined to output an inference and prevention strategy for the training wildfire based on the training target failure probability, the training power supply information, and the training spread information; the inference and prevention strategy includes cutting off the power supply to the transmission line or maintaining the power supply to the transmission line. Determine the fire risk cost of maintaining power supply to the transmission line according to the aforementioned reasoning and prevention strategy; Determine the load loss cost under the condition that the power supply to the transmission line is cut off according to the aforementioned reasoning and prevention strategy; Based on the fire risk cost and the load loss cost, determine the initial evaluation score of the reasoning prevention and control strategy, and based on the initial evaluation score, determine whether the updated neural network model meets the preset model training objective; If the updated neural network model satisfies the model training objective, then the updated neural network model will be used as the wildfire prevention and control model.

11. The method for preventing wildfires along transmission lines according to claim 10, characterized in that, The step of determining whether the updated neural network model meets the preset model training objective based on the initial evaluation score includes: When the training wildfire is controlled according to the aforementioned reasoning and control strategy, the inference current of the transmission line is determined. If the inference current is not less than the dynamic rated current, then the initial evaluation score is reduced by using a preset safety cost function to obtain the target evaluation score; If the target evaluation score is not less than the preset evaluation score threshold, then the updated neural network model is confirmed to meet the model training objective.

12. A wildfire prevention device for power transmission lines, characterized in that, The wildfire prevention and control device, applied to power transmission lines, includes: The acquisition module is used to acquire the size and location information of power transmission lines affected by wildfires. The thermal balance relationship determination module is used to determine the thermal balance parameters of the transmission line under the influence of the wildfire based on the size information, the line location information and the wildfire information, and to determine the thermal balance relationship of the transmission line under the influence of the wildfire using the thermal balance parameters and the current actual current of the transmission line. The first fault probability determination module is used to determine the dynamic rated current of the transmission line under the influence of the wildfire based on the thermal balance relationship, and to determine the first fault probability of the transmission line based on the dynamic rated current and the actual current. The first wildfire prevention module is used to prevent wildfires from spreading on the transmission line based on the first fault probability.

13. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method as described in any one of claims 1 to 11.

14. 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 method as described in any one of claims 1 to 11.

Images