Power system disaster vulnerability evaluation method, device, equipment and medium
The disaster data of the power system is reduced through K-means clustering and rough set theory. Combined with the RBF neural network, the problem of redundant indicators in the disaster vulnerability evaluation of power system is solved, the evaluation efficiency and accuracy are improved, and the scientific vulnerability assessment.
Patent Information
- Application Number
- CN202411036513.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-12-03
AI Technical Summary
There are redundant indicators in the evaluation of disaster vulnerability of power systems, resulting in increased burden on the prediction model, reduced generalization ability, and low evaluation efficiency and accuracy, especially when processing large amounts of data, the calculation complexity is significantly increased.
The K-means clustering algorithm is used to cluster historical disaster data, synthesize pseudo-attributes, and simplify the rough set theory to build a vulnerability evaluation model, and train it using RBF neural network to generate vulnerability labels to evaluate the power facilities. Vulnerability.
By optimizing the index system, the complexity of the reduction time is reduced, the model's prediction accuracy for disaster losses is improved, and a more accurate assessment of the vulnerability of the power system is provided, providing a scientific basis for formulating improvement plans.
Smart Images

Figure CN119067287A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of disaster prevention of electric power infrastructure, and in particular to a method, device, equipment and medium for evaluating the vulnerability of electric power system to disasters. Background Art
[0002] As the scale and complexity of power systems increase, the impact of disasters on power systems becomes more and more significant. Disaster vulnerability assessment has become an important means to ensure the stable operation of power systems and reduce disaster losses. At present, the disaster vulnerability assessment method of power systems is mainly based on multi-source and multi-factor data analysis.
[0003] However, the indicator system for evaluating the vulnerability of power system disasters is a complex gray system. Redundant indicator information not only increases the burden on the prediction model, but also reduces the generalization ability of the model. When there are a large number of redundant indicators, the evaluators need to spend extra time and energy to screen and identify effective information, which will significantly reduce the efficiency of the evaluation work. Especially when processing a large amount of data, the existence of redundant indicators will greatly increase the complexity of data processing and model calculation. Summary of the invention
[0004] The present invention aims to provide a method, device, equipment and medium for evaluating the disaster vulnerability of a power system to solve the technical problem of how to optimize the evaluation of the disaster vulnerability of a power system to achieve the technical effect of improving the efficiency of the evaluation of the disaster vulnerability of a power system to achieve.
[0005] In order to solve the above technical problems, an embodiment of the present invention provides a method for evaluating the vulnerability of power system to disasters, comprising:
[0006] Acquire historical disaster data of the target power facility area, wherein the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data;
[0007] Constructing a first decision table according to the historical disaster data, clustering the first decision table using a K-means clustering algorithm to obtain a plurality of attribute clusters, synthesizing all attributes in the same attribute cluster into pseudo attributes, and constructing a second decision table according to all the pseudo attributes;
[0008] Simplifying the second decision table by rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility;
[0009] Constructing a vulnerability assessment model, inputting the indicator data into the vulnerability assessment model for training, and obtaining a trained vulnerability assessment model;
[0010] Obtain disaster indicator data to be assessed, input the disaster indicator data to be assessed into a trained vulnerability assessment model, obtain disaster data of the target power facility, and generate a vulnerability label of the target power facility according to the disaster data.
[0011] As one preferred solution, the obtaining of historical disaster data of the target power facility area further includes:
[0012] Acquire structural data and non-structural data of the target power facility area;
[0013] The unstructured data is structured, and the structured data is fused with the structured data to obtain fused data.
[0014] As one preferred solution, the obtaining of historical disaster data of the target power facility area includes:
[0015] Obtain disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data for the target power facility area, wherein the disaster type data includes: magnitude, focal depth, epicenter distance, flood water level, flow velocity, inundation range, wind speed, wind direction, rainfall, fire size, fire source location, and burning material;
[0016] The impact range data include: the area of the disaster-affected area, population density, economic development level, number of substations, substation capacity, length of transmission lines, installed capacity of power stations, and power generation type of power stations;
[0017] The rescue difficulty data include: the complexity of the disaster area terrain, weather conditions in the disaster area, traffic conditions in the disaster area, the number of rescue personnel, the number of emergency power generation equipment, the number of spare materials, and the funds required for rescue;
[0018] The post-disaster recovery data includes: facility repair time, network reconstruction time, equipment purchase cost, maintenance cost, and labor cost.
[0019] As one preferred solution, the step of performing structured processing on the unstructured data and fusing the structured processed data with the structured data to obtain fused data includes:
[0020] Acquire unstructured data, wherein the unstructured data includes but is not limited to one or more of the following data: documents, images, voice, and video;
[0021] Performing data, format conversion, and denoising operations on the unstructured data in sequence to obtain standardized data;
[0022] Extracting features from the standardized data using a machine learning method to obtain unstructured data features;
[0023] Extracting features from the structured data using a machine learning method to obtain structured data features;
[0024] The unstructured data features and the structured data features are fused to obtain fused features.
[0025] As one of the preferred solutions, synthesizing all attributes in the same attribute cluster into pseudo attributes includes:
[0026] The average value of all attributes in the same attribute cluster is taken as the pseudo-attribute of the attribute cluster.
[0027] As one of the preferred solutions, the second decision table is simplified by rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility, including:
[0028] Obtaining weight coefficients of all pseudo attributes of the first sample in the second decision table, where the weight coefficients reflect the importance of the pseudo attributes;
[0029] The pseudo attribute with the largest weight coefficient is used as the simplified result of the first sample.
[0030] As one preferred solution, generating the vulnerable label of the target power facility according to the disaster data includes:
[0031] Determine the degree of damage caused by the fault according to the disaster data; wherein the degree of damage caused by the fault includes the degree of power damage and the degree of economic loss;
[0032] A vulnerability label of the target power facility is generated according to the fault damage degree information and the disaster indicator data to be assessed, and a vulnerability assessment result of the target power facility is obtained according to the vulnerability label.
[0033] Another embodiment of the present invention provides a power system disaster vulnerability assessment device, comprising:
[0034] An acquisition module is used to acquire historical disaster data of a target power facility area, wherein the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data;
[0035] A construction module, used to construct a first decision table according to the historical disaster data, cluster the first decision table using a K-means clustering algorithm to obtain multiple attribute clusters, synthesize all attributes in the same attribute cluster into pseudo attributes, and construct a second decision table according to all the pseudo attributes;
[0036] A simplification module, used for simplifying the second decision table by using rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility;
[0037] A training module, used for constructing a vulnerability assessment model, inputting the indicator data into the vulnerability assessment model for training, and obtaining a trained vulnerability assessment model;
[0038] A generation module is used to obtain disaster indicator data to be evaluated, input the disaster indicator data to be evaluated into a trained vulnerability assessment model, obtain disaster data of the target power facility, and generate a vulnerability label of the target power facility based on the disaster data.
[0039] Another embodiment of the present invention provides a power system disaster vulnerability assessment device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the power system disaster vulnerability assessment method as described above.
[0040] Yet another embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the method for evaluating the disaster vulnerability of a power system as described above is implemented.
[0041] Compared with the prior art, the embodiments of the present invention have the following advantages:
[0042] 1) The present invention assesses external threats such as natural disasters and man-made accidents that the power system may face, which helps to take corresponding preventive measures before the disaster occurs and reduce the impact and loss of the disaster on the power system.
[0043] 2) The present invention takes into account the impact of multiple risk factors on the operation of the power system, including natural factors (such as earthquakes, floods, hurricanes, etc.), human factors (such as equipment failures, operational errors, etc.), etc. This comprehensive evaluation method can more accurately reflect the vulnerability of the power system and provide a scientific basis for the formulation of improvement plans.
[0044] 3) The present invention simplifies the complex indicator system by introducing rough set theory, deletes some useless factors without the need for prior knowledge, and optimizes the input variables of the prediction model. At the same time, the present invention forms a new decision-making information system through pseudo-attributes, which significantly improves the time complexity of solving the simplification.
[0045] 4) The present invention utilizes the advantages of the RBF neural network model in solving uncertainty problems. By optimizing and simplifying the original prediction system data, it effectively identifies and extracts the prediction factors closely related to the damage to power facilities, and significantly improves the model's prediction accuracy for disaster losses. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] Figure 1 It is a flow chart of a method for evaluating the vulnerability of power system to disasters in one embodiment of the present invention;
[0047] Figure 2 It is a structural schematic diagram of a power system disaster vulnerability assessment device in one embodiment of the present invention;
[0048] Figure 3 It is a schematic diagram of a power system disaster vulnerability assessment device in one embodiment of the present invention. DETAILED DESCRIPTION
[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0050] In the description of this application, the terms "first", "second", "third", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", "third", etc. may explicitly or implicitly include one or more of the feature. In the description of this application, unless otherwise specified, "plurality" means two or more.
[0051] In the description of the present application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. The terms "vertical", "horizontal", "left", "right", "upper", "lower" and similar expressions used herein are only for illustrative purposes, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.
[0052] In the description of this application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood by specific circumstances.
[0053] An embodiment of the present invention provides a method for evaluating the vulnerability of power system to disasters. Figure 1 , Figure 1 The flowchart of the method for evaluating the disaster vulnerability of a power system provided in one embodiment of the present invention is shown. It includes steps S1 to S4:
[0054] S1. Obtain historical disaster data of the target power facility area, where the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data;
[0055] Electric power data includes multiple types, both structured and unstructured. Analyzing data in only one mode will obviously lose valuable information in other modes, and thus cannot effectively make predictions based on the data. Specifically, structured data refers to data with fixed formats and rules, presented in the form of tables, tree structures or relational models, such as the voltage, current, and output power changes of generators. Unstructured data refers to data without fixed formats and rules, including office documents, technical documents, texts, pictures, XML files, HTML files, various reports, images, audio files, video files, etc. in all formats.
[0056] In the embodiment of the present invention, preferably, obtaining historical disaster data of the target power facility area also includes:
[0057] Acquire structural data and non-structural data of the target power facility area;
[0058] The unstructured data is structured and the structured data is fused with the structured data to obtain fused data.
[0059] In the embodiment of the present invention, preferably, the unstructured data is structured, and the structured data is fused with the structured data to obtain fused data, including:
[0060] Access unstructured data;
[0061] Performing data, format conversion, and denoising operations on the unstructured data in sequence to obtain standardized data;
[0062] Extracting features from the standardized data using a machine learning method to obtain unstructured data features;
[0063] Extracting features from the structured data using a machine learning method to obtain structured data features;
[0064] The unstructured data features and the structured data features are fused to obtain fused data.
[0065] Specifically, the method of machine learning includes extracting data through a neural network. The neural network includes a GRU-CNN network module and a Transformer network module, wherein the GRU-CNN network module is a GRU-CNN mixed stacking block, and the GRU-CNN mixed stacking block is composed of Nbc GRU-CNN blocks stacked, and each GRU-CNN block is composed of a BiGRU network with an attention mechanism and a multi-dilation convolution network (Mut-dilatation CNN). The Transformer network module includes N, Transformer Encode blocks, wherein each Transformer Encoder block includes a multi-head self-attention mechanism layer, a fully connected layer and a normalization layer.
[0066] The present invention takes into account the impact of multiple risk factors on the operation of the power system, including natural factors, human factors, etc. This comprehensive evaluation method can more accurately reflect the vulnerability of the power system and provide a scientific basis for formulating improvement plans.
[0067] In the embodiment of the present invention, preferably, obtaining historical disaster data of the target power facility area includes:
[0068] Obtain disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data for the target power facility area, wherein the disaster type data includes: magnitude, focal depth, epicenter distance, flood water level, flow velocity, inundation range, wind speed, wind direction, rainfall, fire size, fire source location, and burning materials;
[0069] The impact range data include: the area of the disaster-affected area, population density, economic development level, number of substations, substation capacity, length of transmission lines, installed capacity of power stations, and power generation type of power stations;
[0070] The rescue difficulty data include: the complexity of the disaster area terrain, weather conditions in the disaster area, traffic conditions in the disaster area, the number of rescue personnel, the number of emergency power generation equipment, the number of spare materials, and the funds required for rescue;
[0071] The post-disaster recovery data includes: facility repair time, network reconstruction time, equipment purchase cost, maintenance cost, and labor cost.
[0072] S2. Construct a first decision table according to the historical disaster data, apply K-means clustering algorithm to cluster the first decision table to obtain multiple attribute clusters, synthesize all attributes in the same attribute cluster into pseudo attributes, and construct a second decision table according to all the pseudo attributes;
[0073] The present invention reduces the dimension of high-dimensional data from the aspect of attribute similarity, unifies similar original attributes into a pseudo-attribute, and then simplifies the pseudo-attribute, effectively compresses the search space for data attributes, significantly reduces the time consumption of simplification, and improves the classification accuracy and classification performance of attribute simplification. At the same time, the K-means clustering algorithm is used to realize the division of attribute clusters, and several similar attributes contained in the generated attribute clusters are synthesized into pseudo-attributes, and all pseudo-attributes are formed into a new decision information system, which effectively reduces redundant attributes.
[0074] In the embodiment of the present invention, preferably, the average value of all attributes in the same attribute cluster is used as the pseudo attribute of the attribute cluster.
[0075] Specifically, the first decision table is expressed as: DS = <U, A∪({d})>, R, where U is a non-empty finite set of samples, A is an attribute set consisting of all conditional attributes, d is a decision attribute, and R is a reduced result set.
[0076] The second decision table is expressed as: DS′=<U,A′∪({d})>,R′, where U is a non-empty finite set of samples, A′ is all pseudo-attributes, d is the decision attribute, and R is the new reduction result set.
[0077] S3. Simplifying the second decision table by rough set theory to obtain disaster index data reflecting the vulnerability of the target power facility to disasters;
[0078] In the embodiment of the present invention, preferably, the weight coefficients of all pseudo attributes of the first sample in the second decision table are obtained, and the weight coefficients reflect the importance of the pseudo attributes;
[0079] The pseudo attribute with the largest weight coefficient is taken as the reduction result of the first sample.
[0080] The calculation formula of importance is: In the formula, a is a pseudo-attribute, d is the decision attribute, A′ is the pseudo attribute set, R′ is the new reduction result set; δ>0, is a measure of attribute reduction, which is the approximate quality or conditional entropy.
[0081] S4, constructing a vulnerability assessment model, inputting the indicator data into the vulnerability assessment model for training, and obtaining a trained vulnerability assessment model;
[0082] Due to the complexity and transient nature of power disasters, the action mechanism and influence mechanism between the disaster and the prediction factors are difficult to simulate with ordinary linear regression models. In view of the complex coupled nonlinear relationship between the disaster and the prediction factors, the present invention uses the RBF neural network model to perform fuzzy quantitative prediction of disaster losses. The RBF neural network is an efficient feedforward neural network. This neural network model has a simple structure, efficient training, optimal approximation performance and global optimal characteristics, can realize the modeling of nonlinear systems, and has good generalization ability. The RBF neural network consists of an input layer, a hidden layer, and an output layer. Among them, there is a simple nonlinear mapping between the input layer and the hidden layer. The radial basis function in the hidden layer is responsible for processing the input variables, and then linearly mapping them to the output layer.
[0083] The training process of the RBF neural network specifically includes:
[0084] Step 1: Initialize the neural network parameters, configure the learning rate and iteration accuracy;
[0085] Step 2: Calculate the value of the root mean square error of the network output. If the value of the root mean square error is less than or equal to the iteration accuracy, the training is terminated, otherwise, step 3 is executed;
[0086] Step 3: Use the gradient descent method to iteratively train the weight parameters, center parameters, and width parameters of the neural network model, and then execute step 2.
[0087] S5. Obtain the disaster indicator data to be assessed, input the disaster indicator data to be assessed into the trained vulnerability assessment model, obtain the disaster data of the target power facility, and generate the vulnerability label of the target power facility according to the disaster data.
[0088] In the embodiment of the present invention, preferably, generating a vulnerable label of a target power facility according to the disaster data includes:
[0089] Determine the extent of the fault damage based on the disaster data; the extent of the fault damage includes the extent of power damage and the extent of economic loss;
[0090] According to the fault damage degree information and the disaster indicator data to be assessed, the vulnerability label of the target power facility is generated, and the vulnerability assessment result of the target power facility is obtained according to the vulnerability label.
[0091] Specifically, you can use or Calculate the degree of power damage, where ω D is the degree of power damage, V P and V P ′ represents the number of nodes in the target power system before and after the fault, E P and E′P They represent the number of branches of the target power system before and after the fault respectively;
[0092] use Calculate the degree of economic loss, where ω C is the degree of economic loss, P O and P O ′ represent the total power of the target power system generator and the power adjustment of the faulty dispatched generator respectively.
[0093] Another embodiment of the present invention provides a power system disaster vulnerability assessment device. For details, see Figure 2 , Figure 2 The structure diagram of the power system disaster vulnerability assessment device provided in one embodiment of the present invention is shown, and the power system disaster vulnerability assessment device includes an acquisition module 11, a construction module 12, a simplification module 13, a training module 14, and a generation module 15, wherein:
[0094] An acquisition module 11 is used to acquire historical disaster data of a target power facility area, wherein the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data;
[0095] A construction module 12 is used to construct a first decision table according to historical disaster data, cluster the first decision table using a K-means clustering algorithm to obtain multiple attribute clusters, synthesize all attributes in the same attribute cluster into pseudo attributes, and construct a second decision table according to all pseudo attributes;
[0096] A simplification module 13 is used to simplify the second decision table by using rough set theory to obtain disaster index data reflecting the vulnerability of target power facilities to disasters;
[0097] The training module 14 is used to construct a vulnerability assessment model, input the indicator data into the vulnerability assessment model for training, and obtain a trained vulnerability assessment model;
[0098] The generation module 15 is used to obtain the disaster indicator data to be evaluated, input the disaster indicator data to be evaluated into the trained vulnerability assessment model, obtain the disaster data of the target power facility, and generate the vulnerability label of the target power facility according to the disaster data.
[0099] Another embodiment of the present invention provides a power system disaster vulnerability assessment device. For details, see Figure 3 , Figure 3The figure shows a schematic diagram of a power system disaster vulnerability assessment device provided in one embodiment of the present invention. The power system disaster vulnerability assessment device includes a processor 21, a memory 22, and a computer program stored in the memory 22 and configured to be executed by the processor 21. When the processor 21 executes the computer program, the steps in the above-mentioned power system disaster vulnerability assessment method embodiment are implemented, for example Figure 1 or, the processor 21 implements the functions of each module in the above-mentioned device embodiments, such as the acquisition module 11, when executing the computer program.
[0100] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 22 and executed by the processor 21 to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the power system disaster vulnerability assessment device. For example, the computer program may be divided into an acquisition module 11, a construction module 12, a simplification module 13, a training module 14, and a generation module 15.
[0101] The processor 21 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 21 is the control center of the power system disaster vulnerability assessment device, and uses various interfaces and lines to connect various parts of the entire power system disaster vulnerability assessment device.
[0102] The memory 22 can be used to store the computer program and / or module. The processor 21 realizes various functions of the power system disaster vulnerability assessment device by running or executing the computer program and / or module stored in the memory 22 and calling the data stored in the memory 22. The memory 22 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory 22 can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0103] Wherein, if the module integrated in the power system disaster vulnerability assessment device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned method embodiments can be implemented. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium.
[0104] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
[0105] Accordingly, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the steps in the power system disaster vulnerability assessment method of the above embodiment, for example Figure 1 Steps S1 to S5 described in .
[0106] Compared with the prior art, the embodiments of the present invention have the following advantages:
[0107] 1) The present invention assesses external threats such as natural disasters and man-made accidents that the power system may face, which helps to take corresponding preventive measures before the disaster occurs and reduce the impact and loss of the disaster on the power system.
[0108] 2) The present invention takes into account the impact of multiple risk factors on the operation of the power system, including natural factors (such as earthquakes, floods, hurricanes, etc.), human factors (such as equipment failures, operational errors, etc.), etc. This comprehensive evaluation method can more accurately reflect the vulnerability of the power system and provide a scientific basis for the formulation of improvement plans.
[0109] 3) The present invention simplifies the complex indicator system by introducing rough set theory, deletes some useless factors without the need for prior knowledge, and optimizes the input variables of the prediction model. At the same time, the present invention forms a new decision-making information system through pseudo-attributes, which significantly improves the time complexity of solving the simplification.
[0110] 4) The present invention utilizes the advantages of the RBF neural network model in solving uncertainty problems. By optimizing and simplifying the original prediction system data, it effectively identifies and extracts the prediction factors closely related to the damage to power facilities, and significantly improves the model's prediction accuracy for disaster losses.
[0111] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.
Claims
1. A method for evaluating the vulnerability of power system to disasters. It is characterized in that The following steps are involved: Acquire historical disaster data of the target power facility area, wherein the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data; Constructing a first decision table according to the historical disaster data, clustering the first decision table using a K-means clustering algorithm to obtain a plurality of attribute clusters, synthesizing all attributes in the same attribute cluster into pseudo attributes, and constructing a second decision table according to all the pseudo attributes; Simplifying the second decision table by rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility; Constructing a vulnerability assessment model, inputting the indicator data into the vulnerability assessment model for training, and obtaining a trained vulnerability assessment model; Obtain disaster indicator data to be assessed, input the disaster indicator data to be assessed into a trained vulnerability assessment model, obtain disaster data of the target power facility, and generate a vulnerability label of the target power facility according to the disaster data.
2. The method for evaluating the vulnerability of power system to disasters according to claim 1, It is characterized in that The obtaining of historical disaster data of the target power facility area also includes: Acquire structural data and non-structural data of the target power facility area; The unstructured data is structured, and the structured data is fused with the structured data to obtain fused data.
3. The method for evaluating the vulnerability of power system to disasters according to claim 1, It is characterized in that The obtaining of historical disaster data of the target power facility area includes: Obtain disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data for the target power facility area, wherein the disaster type data includes: magnitude, focal depth, epicenter distance, flood water level, flow velocity, inundation range, wind speed, wind direction, rainfall, fire size, fire source location, and burning material; The impact range data include: the area of the disaster-affected area, population density, economic development level, number of substations, substation capacity, length of transmission lines, installed capacity of power stations, and power generation type of power stations; The rescue difficulty data include: the complexity of the disaster area terrain, weather conditions in the disaster area, traffic conditions in the disaster area, the number of rescue personnel, the number of emergency power generation equipment, the number of spare materials, and the funds required for rescue; The post-disaster recovery data includes: facility repair time, network reconstruction time, equipment purchase cost, maintenance cost, and labor cost.
4. The method for evaluating the vulnerability of power system to disasters according to claim 2, It is characterized in that The step of performing structured processing on the unstructured data and fusing the structured processed data with the structured data to obtain fused data includes: Acquire unstructured data, wherein the unstructured data includes but is not limited to one or more of the following data: documents, images, voice, and video; Performing data, format conversion, and denoising operations on the unstructured data in sequence to obtain standardized data; Extracting features from the standardized data using a machine learning method to obtain unstructured data features; Extracting features from the structured data using a machine learning method to obtain structured data features; The unstructured data features and the structured data features are fused to obtain fused features.
5. The method for evaluating the vulnerability of power system to disasters according to claim 1, It is characterized in that The step of synthesizing all attributes in the same attribute cluster into pseudo attributes includes: The average value of all attributes in the same attribute cluster is taken as the pseudo-attribute of the attribute cluster.
6. The method for evaluating the vulnerability of power system to disasters according to claim 1, It is characterized in that The method of simplifying the second decision table by using rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility includes: Obtaining weight coefficients of all pseudo attributes of the first sample in the second decision table, where the weight coefficients reflect the importance of the pseudo attributes; The pseudo attribute with the largest weight coefficient is used as the simplified result of the first sample.
7. The method for evaluating the vulnerability of power system to disasters according to claim 1, It is characterized in that The generating of the vulnerable label of the target electric power facility according to the disaster data includes: Determine the degree of damage caused by the fault according to the disaster data; wherein the degree of damage caused by the fault includes the degree of power damage and the degree of economic loss; A vulnerability label of the target power facility is generated according to the fault damage degree information and the disaster indicator data to be assessed, and a vulnerability assessment result of the target power facility is obtained according to the vulnerability label.
8. A power system disaster vulnerability assessment device, It is characterized in that Includes the following modules: An acquisition module is used to acquire historical disaster data of a target power facility area, wherein the historical disaster data includes disaster type data, impact range data, rescue difficulty data, and post-disaster recovery data; A construction module, used to construct a first decision table according to the historical disaster data, cluster the first decision table using a K-means clustering algorithm to obtain multiple attribute clusters, synthesize all attributes in the same attribute cluster into pseudo attributes, and construct a second decision table according to all the pseudo attributes; A simplification module, used for simplifying the second decision table by using rough set theory to obtain disaster index data reflecting the disaster vulnerability of the target power facility; A training module, used for constructing a vulnerability assessment model, inputting the indicator data into the vulnerability assessment model for training, and obtaining a trained vulnerability assessment model; A generation module is used to obtain disaster indicator data to be evaluated, input the disaster indicator data to be evaluated into a trained vulnerability assessment model, obtain disaster data of the target power facility, and generate a vulnerability label of the target power facility based on the disaster data.
9. A power system disaster vulnerability assessment device, It is characterized in that The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for evaluating the disaster vulnerability of a power system as described in any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for evaluating the disaster vulnerability of a power system as described in any one of claims 1 to 7 is implemented.
