A method and system for assessing urban power supply risks under natural disasters

Abstract

The present invention provides a method and system for assessing urban power supply risks under the influence of natural disasters. The method comprises: collecting and verifying basic data of power grids in a pre-selected risk assessment area; screening risk assessment model data for urban power supply risk assessment from the basic power grid data according to preset rules; based on a pre-built urban power grid component outage probability model dominated by disaster-causing factors under different disasters, taking the risk assessment model data as input to obtain risk assessment index values ​​outputted respectively by the outage probability model; taking the risk assessment index values ​​outputted respectively by the outage probability model and the corresponding disaster-causing factors and urban power grid components as inputs of a pre-trained association model, and outputting an urban power supply risk assessment result including the spatiotemporal distribution of the power outage area; wherein the training set of the association model includes a fusion code of the disaster-causing factors, urban power grid components and risk assessment index values, and annotated spatiotemporal distribution code labels of the power outage area.

Description

Technical Field

[0001] The present application belongs to the technical field of urban power supply risk assessment, and in particular relates to a method and system for urban power supply risk assessment under the influence of natural disasters. Background Art

[0002] Safe and reliable power supply is an important foundation for economic development and people's livelihood.

[0003] The power grid is responsible for urban power supply risk assessment, disaster emergency preparedness and emergency response. Risk assessment is one of the important indicators for evaluating the quality of urban power grid planning schemes. It is particularly important to take precautions in the early stages and conduct urban power supply risk assessment before natural disasters occur.

[0004] Existing emergency risk analysis mainly focuses on safety risk prediction for local subsystems or equipment of the power supply system, without considering the correlation between disaster events and power outage areas.

[0005] Therefore, how to provide a method and system for urban power supply risk assessment under the influence of natural disasters that can comprehensively consider the correlation between disaster events and power outage areas is a technical problem that needs to be solved urgently. Summary of the Invention

[0006] The present application provides a method for assessing urban power supply risks under the influence of natural disasters, which includes: collecting and verifying basic data of the power grid in a pre-selected risk assessment area; screening risk assessment model data for urban power supply risk assessment from the basic power grid data according to preset rules; based on a pre-built urban power grid component outage probability model dominated by disaster-causing factors under different disasters, taking the risk assessment model data as input, and obtaining risk assessment index values ​​output by the outage probability model respectively; taking the risk assessment index values ​​output by the outage probability model and the corresponding disaster-causing factors and urban power grid components as inputs of a pre-trained association model, and outputting an urban power supply risk assessment result including the spatiotemporal distribution of the power outage area; wherein the training set of the association model includes a fusion code of the disaster-causing factors, urban power grid components and risk assessment index values, and annotated spatiotemporal distribution code labels of the power outage area, and the urban power supply risk assessment model is a prediction model based on deep learning.

[0007] By adopting the above scheme, the outage probability model of urban power grid components dominated by disaster-causing factors under different disasters can be integrated to analyze and obtain the risk assessment index values ​​corresponding to different disaster-causing factors. Then, based on the pre-trained association model, the correlation between disaster-causing factors, urban power grid components, risk assessment index values ​​and the spatiotemporal distribution of power outage areas can be learned, thereby obtaining the urban power supply risk assessment results including the spatiotemporal distribution of power outage areas.

[0008] In some embodiments of the present invention, the risk assessment model data input into the urban power grid component outage probability model includes various disaster-causing factors, urban power grid components, and the operation mode of the components in the power grid; wherein the disaster-causing factors include multiple types of extreme weather, earthquakes, wind and rain, urban flooding, and cyber attacks.

[0009] In some embodiments of the present invention, the type of the urban power grid component outage probability model is an optimal power flow model or a load reduction optimal model, and the urban power grid component outage probability model includes a load loss assessment model. During the training process of the load loss assessment model, a training set is constructed based on a load classification method.

[0010] In some embodiments of the present invention, during the training of the urban power grid component outage probability model, the method further includes: generating fault scenarios by sampling based on the Monte Carlo method, and encoding the spatiotemporal distribution of the power outage area based on the risk assessment model data statistics.

[0011] In some embodiments of the present invention, during the training process of the association relationship model, the method further includes: improving the generalization ability of the model based on an integrated learning approach, and adjusting the training process using a category balance and overfitting suppression approach.

[0012] In some embodiments of the present invention, for the output of the urban power grid component outage probability model, the method also includes: weighting the risk assessment index values ​​output by each outage probability model based on the power outage loss model, so as to use the weighted risk assessment index values ​​as the input of the association model.

[0013] In some embodiments of the present invention, the method also includes: for an association relationship model with a weighted risk assessment index value as input, using fuzzy information entropy evaluation to evaluate the urban power grid risk from multiple dimensions, and outputting an urban power supply risk assessment result that also includes a risk weight.

[0014] Correspondingly, on the other hand, the present invention proposes a system for assessing urban power supply risks under the influence of natural disasters, comprising a processor, a memory, and a computer program / instructions stored in the memory, wherein the processor is used to execute the computer program / instructions, and when the computer program / instructions are executed, the system implements the steps of the method described in the above embodiment.

[0015] Accordingly, another aspect of the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon, which implements the steps of the method described in the above embodiment when the computer program / instruction is executed by a processor.

[0016] Accordingly, another aspect of the present invention provides a computer program product, comprising a computer program / instruction, which implements the steps of the method described in the above embodiment when executed by a processor.

[0017] Additional advantages, objects, and features of the present invention will be described in part in the following description and will become apparent to those skilled in the art after studying the following or may be learned by practice of the present invention. The objects and other advantages of the present invention may be particularly pointed out and attained in the description and drawings.

[0018] Those skilled in the art will understand that the purposes and advantages that can be achieved by the present invention are not limited to the above specific descriptions, and the above and other purposes that can be achieved by the present invention will be more clearly understood based on the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide further understanding of the present disclosure and constitute a part of the specification. Together with the following detailed description, they are used to explain the present disclosure, but do not constitute a limitation of the present disclosure.

[0020] In the attached figure:

[0021] Figure 1 This is a flow chart of a method for assessing urban power supply risks under natural disasters according to an embodiment of the present invention.

[0022] Figure 2 This is a flow chart of a method for assessing urban power supply risks under natural disasters according to another embodiment of the present invention.

[0023] Figure 3 This is a schematic diagram of the principle of the present invention for urban power supply risk assessment under the influence of natural disasters.

[0024] Figure 4 This is a complete technical roadmap for the risk assessment of urban power supply under natural disasters. DETAILED DESCRIPTION

[0025] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features therein can be combined with each other in the absence of conflict.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0027] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprises" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method, article or device that includes the elements.

[0028] To overcome the challenges of existing technologies, this paper proposes a method and system for assessing urban power supply risks under natural disasters. This method and system focuses on the natural disasters and emergencies that primarily impact urban distribution networks, as well as their causal mechanisms. By assessing their impact on the safe operation of urban power grids, the system constructs a deep learning-based spatiotemporal correlation model of disasters, power grids, and power outages. This model helps reveal the correlation between major disasters and power outage areas, enabling accurate assessment of urban power grid outage risks under emergencies.

[0029] The general definition of risk is "the probability of harm or loss to people or property." In actual engineering evaluation, the widely accepted definition of risk is the potential for damage to occur within a certain period of time when humans engage in certain activities. This damage is derived from two aspects: likelihood (probability P) and severity (consequence C). The risk value is simply the product of these two: R = P·C. Therefore, when conducting a risk assessment of an uncertain event, a comprehensive evaluation of both the likelihood and severity of the event is necessary. One should not only consider the probability of a failure, or overemphasize the impact or loss of a failure while ignoring the likelihood of the event itself. Only by comprehensively considering the probability of an event and the severity of its consequences can the risk be truly and comprehensively reflected.

[0030] The risk analysis of power grid emergencies is a quantitative analysis and estimation of the spatiotemporal distribution, intensity, probability of occurrence and possible consequences of emergencies that may occur to the power grid infrastructure in a certain area in the future.

[0031] Grid risk stems from the complexity and uncertainty of large-scale systems. Taking the urban power grid, the focus of this proposal, as an example, the probabilistic characteristics of device behavior in the system are often difficult to accurately predict, and thus the occurrence of random failures cannot be fully controlled. Objectively and rationally describing power system risk is a fundamental and challenging task. This research should focus on the following aspects: 1) analyzing the outage models of system components; 2) selecting system failure states and calculating their probabilities; 3) evaluating the impact and consequences of these selected system states; and 4) developing quantitative risk indicators.

[0032] The key to risk assessment is to quantitatively assess the likelihood and severity of the uncertainties within the system, thereby building an assessment model and quantitative assessment indicators for urban power grid risk. In other words, when conducting power system risk assessment, it is necessary to consider both the probability of system failure events and the severity of the consequences of these events. Therefore, the general formula for defining the urban power grid risk assessment model is:

[0033] R=P·S (0-1)

[0034] Where: R is the risk level of the urban power grid; P is the probability of a failure event; S is the severity of the consequences of the failure event.

[0035] Since power system risk assessment inevitably involves the related fields of system reliability and system security, it is necessary to clarify the differences and connections between these three concepts and research content, rather than simply assuming that they exist independently and without overlap. In fact, risk, reliability, and security all characterize the operating state of the system to a certain extent, but their respective focuses differ. A comprehensive comparison shows that compared with the research focus of reliability and security, the concept of risk is richer and more comprehensive, and can better describe the uncertainty of power system behavior from a holistic perspective. This is because it not only identifies the probabilistic characteristics of failure events but also reflects the severity of the consequences of these events. Due to the unique network structure of urban power grids, their risk assessment differs from traditional generation and transmission grid risk assessment. In addition to the inability of traditional assessment criteria—the "determinism principle"—to reflect the probabilistic characteristics of urban power grid component failures, load changes, and system behavior, they also fail to fully consider the grid structure of urban power grids. This makes urban power grid risk assessment particularly unique. To this end, this proposal starts with the network topology, considers the variable structure of the grid, conducts a detailed assessment of key equipment, and establishes risk assessment indicators that are more suitable for urban power grids.

[0036] One aspect of the present invention provides a method for assessing urban power supply risks under the influence of natural disasters.

[0037] Figure 1This is a flow chart of a method for assessing urban power supply risk under natural disasters according to an embodiment of the present invention. The method includes the following steps:

[0038] Step S110: Collect and verify basic power grid data within a pre-selected risk assessment area.

[0039] Step S120: Filtering risk assessment model data for urban power supply risk assessment from the power grid basic data according to preset rules.

[0040] Step S130: Based on a pre-built urban power grid component outage probability model dominated by disaster-causing factors under different disasters, the risk assessment model data is used as input to obtain the risk assessment index values ​​output by the outage probability model.

[0041] Step S140: The risk assessment index values ​​and corresponding disaster-causing factors and urban power grid components outputted by the outage probability model are used as inputs of the pre-trained association model, and the urban power supply risk assessment results including the spatiotemporal distribution of the outage area are outputted.

[0042] Among them, the training set of the association relationship model includes the fusion coding of disaster-causing factors, urban power grid components and risk assessment index values, as well as the marked spatiotemporal distribution coding labels of power outage areas. The urban power grid power supply risk assessment model is a prediction model based on deep learning.

[0043] By adopting the above scheme, the outage probability model of urban power grid components dominated by disaster-causing factors under different disasters can be integrated to analyze and obtain the risk assessment index values ​​corresponding to different disaster-causing factors. Then, based on the pre-trained association model, the correlation between disaster-causing factors, urban power grid components, risk assessment index values ​​and the spatiotemporal distribution of power outage areas can be learned, thereby obtaining the urban power supply risk assessment results including the spatiotemporal distribution of power outage areas.

[0044] In some embodiments of the present invention, the risk assessment model data input into the urban power grid component outage probability model includes various disaster-causing factors, urban power grid components, and the operation mode of the components in the power grid; wherein the disaster-causing factors include multiple types of extreme weather, earthquakes, wind and rain, urban flooding, and cyber attacks.

[0045] In some embodiments of the present invention, the type of the urban power grid component outage probability model is an optimal power flow model or a load reduction optimal model, and the urban power grid component outage probability model includes a load loss assessment model. During the training process of the load loss assessment model, a training set is constructed based on a load classification method.

[0046] In some embodiments of the present invention, during the training of the urban power grid component outage probability model, the method further includes: generating fault scenarios by sampling based on the Monte Carlo method, and encoding the spatiotemporal distribution of the power outage area based on the risk assessment model data statistics.

[0047] In some embodiments of the present invention, during the training process of the association relationship model, the method further includes: improving the generalization ability of the model based on an integrated learning approach, and adjusting the training process using a category balance and overfitting suppression approach.

[0048] In some embodiments of the present invention, for the output of the urban power grid component outage probability model, the method also includes: weighting the risk assessment index values ​​output by each outage probability model based on the power outage loss model, so as to use the weighted risk assessment index values ​​as the input of the association model.

[0049] In some embodiments of the present invention, the method also includes: for an association relationship model with a weighted risk assessment index value as input, using fuzzy information entropy evaluation to evaluate the urban power grid risk from multiple dimensions, and outputting an urban power supply risk assessment result that also includes a risk weight.

[0050] Before conducting a risk assessment of the urban power supply system, the urban power grid must be layered from top to bottom according to the direction of the power flow, and when evaluating a certain layer of the power grid, it is assumed that the upper layer directly connected to it is safe and reliable.

[0051] The urban power grid is divided into three main parts according to its topological structure: substation part, distribution trunk line part, and distribution branch feeder part. First, the risks of these three parts are analyzed in detail and their quantitative assessment indicators are established. Then, based on the inherent relationship of risk principles, a comprehensive risk indicator is established. After analyzing and studying the outage models of typical components in the urban power grid, the urban power grid risk assessment process is given, such as Figure 2 As shown, Figure 2 This is a flow chart of a method for assessing urban power supply risks under natural disasters according to another embodiment of the present invention.

[0052] Figure 2 The specific steps are as follows:

[0053] Step S210: Selecting a Risk Assessment Area: Selecting a grid area for which a risk assessment of urban power supply under natural disasters is to be conducted. For example, the division principles of the "Supplementary Explanations to the State Grid Corporation of China on Electric Power Reliability Assessment Procedures (Revised Edition)" can be referenced. Based on these division principles, the topology results of each node (device, subsystem, etc.) within the grid area are set. The assessment scope is primarily selected from representative urban power grids within the city.

[0054] Step S220: Collect and verify the basic data of the power grid in the area: After selecting the evaluation object, collect the equipment data and operation data of the power grid in the area, and verify and screen these data to filter out data that is "harmful" to subsequent evaluation work, so that the final evaluation result is objective and valid.

[0055] Step S230: Exporting risk assessment model data: The filtered and screened reasonable network data is used as the data basis for urban power grid risk assessment and as input data for the established risk assessment model.

[0056] Step S240: Establish risk assessment models for each part and calculate risk assessment indicators: Based on the characteristics of the network topology and the risk principle, construct a reasonable analysis and assessment model for each part of the selected power grid area to form quantitative assessment indicators; then import the above input data to calculate the risk assessment indicators and obtain the risk assessment indicator value (or risk quantification value).

[0057] Step S250: Introduce a power outage loss model to assess the risk of economic costs: In order to make the values ​​of each risk assessment indicator more intuitively reflect the risk level of the urban power grid, adapt to the reform of the power market, and guide the planning or transformation and upgrading work from an economic perspective, it is not possible to only establish technical indicators to quantify the risk. We should also try to describe the risk from an economic perspective. This paper introduces a power outage loss model to solve this problem.

[0058] Step S260: Introduce the fuzzy information entropy evaluation model to evaluate the urban power grid risk from a technical and economic perspective: According to the operating life cycle of the urban power grid, the risk factors are combined with the fuzzy information entropy evaluation model, and finally the urban power grid risk is evaluated from different technical and economic perspectives. The obtained evaluation results are sorted from large to small to find the key high-risk locations in the urban power grid and analyze and optimize them.

[0059] This proposal assesses urban power supply risks and explores their associated characteristics under various natural disasters and emergencies. Different types of natural disasters and emergencies have significantly different impacts on urban power supply risks. For example, power outages caused by urban flooding are often localized, while earthquakes can disrupt power grids in distant cities by damaging transmission grids. By studying urban power supply risk assessment models under different natural disasters and emergencies, we can not only obtain indicators of urban power supply capacity but also identify weaknesses in urban power grids, providing a technical basis for appropriate power grid emergency response plans.

[0060] Figure 3This schematic diagram illustrates the principles of the present invention's urban power supply risk assessment under natural disasters. This approach comprehensively considers the impact of multiple emergencies, using emergency type as a label to analyze the spatiotemporal distribution characteristics of urban power supply risks and power outage areas. The urban power supply risk analysis assesses the risk of the urban power grid under emergencies, while the spatiotemporal distribution analysis explores the spatiotemporal correlations between emergencies and power outage areas.

[0061] This plan mainly conducts urban power supply risk assessment under the influence of natural disasters from two dimensions. Figure 4 This is a complete technical roadmap for the risk assessment of urban power supply under natural disasters.

[0062] Dimension 1: Risk assessment model for urban power grid supply under various natural disasters and emergencies.

[0063] Natural disasters and emergencies will damage urban power grid components, resulting in the destruction of urban power grid connectivity and causing large-scale power outages. Urban power supply risk assessment is an important basis for effective pre-disaster emergency preparedness.

[0064] This proposal first addresses the major natural disasters and emergencies that urban power grids may be subject to. For example, a region is susceptible to sudden natural disasters such as earthquakes and high temperatures, as well as the resulting chain disasters (e.g., earthquakes and heavy rains trigger secondary disasters such as landslides, mudslides, and barrier lakes, which in turn lead to secondary disasters such as building damage, traffic disruptions, and communication interruptions). It then constructs a model for the probability of urban power grid component outages, driven by hazard-causing factors, under different disasters and emergencies, and proposes a method for generating extreme scenarios for urban power grids. This approach further analyzes the essential loads that ensure basic urban operations and critical loads with significant socioeconomic impacts. It also considers the expected impact of power outages on medical institutions, water supply units, and urban transportation infrastructure. It then studies a load loss assessment model for urban power grids under extreme scenarios and proposes a risk assessment model for urban power grids under natural disasters and emergencies.

[0065] Dimension 2: A deep learning-based method for mining the spatiotemporal association between emergencies and urban power grid blackout areas. Major power outages caused by natural disasters and emergencies result in enormous losses but have an extremely low probability. Extensive analysis and calculation are required to determine the possible impact on urban power grids. Efficiently and quickly obtaining possible blackout areas is an important basis for effective emergency response. This approach first analyzes the key factors affecting the urban distribution network caused by natural disasters and emergencies, as well as the spatiotemporal distribution characteristics of power outage areas under historical emergencies in cities and surrounding areas. It then studies the encoding methods for emergency characteristics, power grid operation modes, and the spatiotemporal distribution of power outage areas. It also analyzes the loss characteristics of different types of loads and constructs a correlation model between urban distribution networks and emergencies. On this basis, a method for mining the association relationship of multi-source heterogeneous data based on deep learning algorithms is studied to obtain implicit association rules for each relevant factor and quickly obtain the urban power grid blackout areas that may be caused by emergencies.

[0066] Furthermore, in another embodiment of the present invention, constructing a risk assessment model for urban power grid power supply under the influence of various natural disasters and emergencies can reveal the impact of natural disasters and emergencies on the urban power grid, which is conducive to improving the power supply capacity of the urban power grid.

[0067] This embodiment of the present invention focuses on a city's urban area, collecting historical regional power outage data. Based on the natural disasters and emergencies that the city's power grid has primarily suffered and their causal mechanisms, it analyzes the hazard factors and key elements that affect the safe operation of the city's power grid. It also develops outage models for different components in the power system due to natural disasters and emergencies, analyzing the impact of emergencies on power system operation and the causes of equipment failure. To quantify the impact of emergencies on the safe operation of the power system, it combines theoretical methods such as probability theory and mathematical statistics to establish a probability distribution function for the hazard factors or key elements in emergencies. Based on the relationship between each device's failure conditions and the hazard factors or key elements, it establishes a failure probability model for components in the city's power grid under the influence of emergencies. Focusing on key power supply facilities within the city, it considers different types of loads, such as medical institutions, water supply units, and urban transportation, and analyzes the expected impact of power outages on each type of load. Taking into account the probability of emergencies and the probability of equipment outages, it combines methods such as the optimal power flow model and the load shedding optimal model to establish a city power supply risk assessment model, accurately and effectively assessing the operational risk of the power system affected by emergencies. Finally, the scenario method is used to generate sufficient samples and extract the impact correlation chain of "event-line-distribution network-load"; based on the deep learning method, the fusion coding of natural disasters, emergencies, power grid operation modes, etc. is used as input, and the corresponding coding of the spatiotemporal distribution of power outage areas is used as output. By integrating ensemble learning, category balance, overfitting suppression and other methods, a training model is established that can characterize the correlation relationship between emergencies, power grid operation modes and the spatiotemporal distribution of power outage areas, so as to quickly determine the urban power grid power outage areas that may be caused by emergencies.

[0068] Accordingly, an embodiment of the present application provides a system for assessing urban power supply risks under the influence of natural disasters, the system including a computer device, the computer device including a processor and a memory, the memory storing computer instructions, the processor being used to execute the computer instructions stored in the memory, and when the computer instructions are executed by the processor, the device implements the steps implemented by the above method.

[0069] Accordingly, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the above-mentioned offshore platform safety warning system is implemented.

[0070] It should be understood that the present application is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted here. In the above embodiments, several specific steps are described and illustrated as examples. However, the method process of the present application is not limited to the specific steps described and illustrated. Those skilled in the art can make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present application.

[0071] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium that can store or transmit information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0072] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps. In other words, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0073] Aspects of the present disclosure have been described above with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor or a field programmable logic circuit. It is also understood that each box in the block diagram and / or flowchart and the combination of the boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0074] The above description is only a specific embodiment of the present application. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the scope of protection of the present application.

Claims

1. A method for assessing urban power supply risk under natural disasters, characterized in that: include: Collect and verify basic grid data within the pre-selected risk assessment area; Filter risk assessment model data for urban power supply risk assessment from basic power grid data according to preset rules; Based on the pre-built urban power grid component outage probability model dominated by disaster-causing factors under different disasters, the risk assessment model data is used as input to obtain the risk assessment index values ​​output by the outage probability model; The risk assessment index values ​​and corresponding disaster-causing factors and urban power grid components output by the outage probability model are used as inputs to the pre-trained association model, and the output is the urban power supply risk assessment result including the spatiotemporal distribution of the outage area. For the output of the urban power grid component outage probability model, the method further includes: weighting the risk assessment index values ​​respectively output by each outage probability model based on the power outage loss model, and using the weighted risk assessment index values ​​as input to the association model; For the correlation model with weighted risk assessment index values ​​as input, fuzzy information entropy evaluation is used to evaluate urban power grid risks from multiple dimensions. The output also includes the urban power supply risk assessment results including risk weights. The obtained urban power supply risk assessment results are sorted from large to small to identify key high-risk locations in the urban power grid for analysis and optimization. Among them, the training set of the association relationship model includes the fusion coding of disaster-causing factors, urban power grid components and risk assessment index values, as well as the marked spatiotemporal distribution coding labels of power outage areas. The urban power grid power supply risk assessment model is a prediction model based on deep learning.

2. The method according to claim 1, characterized in that The risk assessment model data input into the urban power grid component outage probability model includes various disaster-causing factors, urban power grid components, and the operation mode of the components in the power grid; wherein the disaster-causing factors include multiple types of extreme weather, earthquakes, wind and rain, urban flooding, and cyber attacks.

3. The method according to claim 2, characterized in that The type of the urban power grid component outage probability model is an optimal power flow model or a load reduction optimal model. The urban power grid component outage probability model includes a load loss assessment model. During the training process of the load loss assessment model, a training set is constructed based on load classification.

4. The method according to claim 1, wherein During the training process of the urban power grid component outage probability model, the method further includes: generating fault scenarios by sampling based on the Monte Carlo method, and encoding the spatiotemporal distribution of the power outage area based on the risk assessment model data statistics.

5. The method according to claim 1, wherein During the training process of the association relationship model, the method further includes: improving the generalization ability of the model based on an integrated learning approach, and adjusting the training process using a category balance and overfitting suppression approach.

6. A system for assessing urban power supply risks under natural disasters, comprising a processor, a memory, and a computer program / instruction stored in the memory, characterized in that: The processor is configured to execute the computer program / instructions. When the computer program / instructions are executed, the system implements the steps of the method according to any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images