Data-driven risk assessment method and decision-making system for power grid emergency repair

Abstract

The present invention discloses a data-driven power grid emergency repair risk assessment method and decision-making system, which relates to the field of power grid operation and maintenance technology. The method includes: constructing a power grid emergency repair database through data-driven collection, analyzing and training the power grid emergency repair database based on a power grid emergency repair risk assessment index system, and generating a power grid emergency repair risk assessment network; using digital twin technology to model the target emergency repair power grid area and build a digital twin model of the power grid emergency repair area; extracting risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment index system to obtain power grid emergency repair risk factor information; and conducting risk assessment and risk emergency repair decision-making on the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network. The technical effect of realizing multi-dimensional indicator intelligent assessment of power grid emergency repair risk, improving the comprehensiveness and accuracy of risk assessment, and thus ensuring the efficiency of emergency repair decision-making is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation and maintenance, and in particular to a data-driven power grid emergency repair risk assessment method and decision-making system. Background Art

[0002] With the development of economy and the improvement of people's living standards, the stable operation of power system is becoming more and more important to people's life and work. However, due to various factors, power grid failure is inevitable. After the failure occurs, timely risk assessment and emergency repair decision-making become crucial. However, the existing emergency repair risk assessment method mainly relies on manual experience and some simple data analysis, which lacks comprehensiveness and accuracy. Summary of the invention

[0003] This application solves the technical problem that the existing emergency repair risk assessment methods lack comprehensiveness and accuracy by providing a data-driven power grid emergency repair risk assessment method and decision-making system, thereby achieving the technical effect of realizing multi-dimensional indicator intelligent assessment of power grid emergency repair risks, improving the comprehensiveness and accuracy of risk assessment, and thus ensuring the efficiency of emergency repair decisions.

[0004] In view of the above problems, the present invention provides a data-driven power grid emergency repair risk assessment method and decision-making system.

[0005] In the first aspect, the present application provides a data-driven power grid emergency repair risk assessment method, the method comprising: obtaining a set of power grid emergency repair risk assessment dimensional indicators, the power grid emergency repair risk assessment dimensional indicator set comprising power grid environment, emergency repair resources, collaborative emergency repair, fault risk and fault time risk; searching and associating based on the power grid emergency repair risk assessment dimensional indicator set to determine a secondary dimensional risk assessment indicator set; building a power grid emergency repair risk assessment indicator system based on the power grid emergency repair risk assessment dimensional indicator set and the secondary dimensional risk assessment indicator set; constructing a power grid emergency repair database through data-driven collection, analyzing and training the power grid emergency repair database based on the power grid emergency repair risk assessment indicator system, and generating a power grid emergency repair risk assessment network; modeling the target emergency repair power grid area using digital twin technology, and building a digital twin model of the power grid emergency repair area; extracting risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment indicator system to obtain power grid emergency repair risk factor information; and conducting risk assessment and risk emergency repair decisions on the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network.

[0006] On the other hand, the present application also provides a data-driven power grid emergency repair risk decision-making system, the system comprising: a risk assessment dimension indicator acquisition module, used to obtain a set of power grid emergency repair risk assessment dimension indicators, the power grid emergency repair risk assessment dimension indicator set comprising power grid environment, emergency repair resources, collaborative emergency repair, fault risk and fault time risk; an indicator search association module, used to search and associate based on the power grid emergency repair risk assessment dimension indicator set to determine a secondary dimensional risk assessment indicator set; a risk assessment indicator system building module, used to build a power grid emergency repair risk assessment indicator system based on the power grid emergency repair risk assessment dimension indicator set and the secondary dimensional risk assessment indicator set; a power grid emergency repair risk assessment indicator system ... A network generation module is used to construct a power grid emergency repair database through data-driven collection, analyze and train the power grid emergency repair database based on the power grid emergency repair risk assessment index system, and generate a power grid emergency repair risk assessment network; a digital twin model construction module is used to use digital twin technology to model the target emergency power grid area and build a digital twin model of the power grid emergency repair area; a risk factor extraction module is used to extract risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment index system to obtain power grid emergency repair risk factor information; a risk assessment decision module is used to perform risk assessment and risk repair decision on the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network.

[0007] In a third aspect, the present application provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and the computer program, when executed by the processor, implements the steps of any one of the above methods.

[0008] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps in any one of the above-mentioned methods when executed by a processor.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] The invention adopts the method of searching and associating based on the set of risk assessment dimensions of power grid repair, determining the set of risk assessment indicators of the secondary dimension, and then building the risk assessment indicator system of power grid repair according to the set of risk assessment dimensions of power grid repair and the set of risk assessment indicators of the secondary dimension; building the power grid repair database through data-driven collection, analyzing and training the power grid repair database based on the power grid repair risk assessment indicator system, and generating the power grid repair risk assessment network; at the same time, using the digital twin technology to model the target power grid repair area, building the digital twin model of the power grid repair area, and then extracting the risk factors of the digital twin model of the power grid repair area based on the power grid repair risk assessment indicator system, and obtaining the risk factor information of power grid repair; and conducting risk assessment and risk repair decision-making on the risk factor information of power grid repair based on the power grid repair risk assessment network. Thus, the technical effect of realizing the intelligent assessment of power grid repair risk with multi-dimensional indicators, improving the comprehensiveness and accuracy of risk assessment, and thus ensuring the efficiency of repair decision-making is achieved.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 A flowchart of a data-driven power grid emergency repair risk assessment method for this application;

[0013] Figure 2 A schematic diagram of a process for determining a set of secondary-dimensional risk assessment indicators in a data-driven power grid emergency repair risk assessment method of this application;

[0014] Figure 3 This is a schematic diagram of the structure of the data-driven power grid emergency repair risk decision-making system for this application;

[0015] Figure 4 This is a schematic diagram of the structure of an exemplary electronic device of the present application.

[0016] Explanation of the accompanying drawings: risk assessment dimension indicator acquisition module 11, indicator search association module 12, risk assessment indicator system construction module 13, power grid emergency repair risk assessment network generation module 14, digital twin model construction module 15, risk factor extraction module 16, risk assessment decision module 17, bus 1110, processor 1120, transceiver 1130, bus interface 1140, memory 1150, operating system 1151, application 1152 and user interface 1160. DETAILED DESCRIPTION

[0017] In the description of the present application, those skilled in the art should know that the present application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, the present application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable 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, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1

[0026] like Figure 1 As shown, the present application provides a data-driven power grid repair risk assessment method, which is applied to a power grid repair risk decision-making system, and the method includes:

[0027] Step S1: obtaining a set of dimensional indicators for power grid emergency repair risk assessment, wherein the set of dimensional indicators for power grid emergency repair risk assessment includes power grid environment, emergency repair resources, collaborative emergency repair, fault risk, and fault time risk;

[0028] Specifically, with the development of the economy and the improvement of people's living standards, the stable operation of the power system has become increasingly important to people's lives and work. However, due to the influence of various factors, power grid failures are inevitable. After the failure occurs, timely risk assessment and emergency repair decisions become crucial. In order to realize the intelligent assessment of power grid emergency repair risks, a set of power grid emergency repair risk assessment dimensional indicators is first formulated. The power grid emergency repair risk assessment dimensional indicator set is the main related indicators of power grid emergency repair risks, including power grid environment, emergency repair resources, collaborative emergency repair, fault risk and fault time risk. The power grid emergency repair risk is comprehensively analyzed through multi-dimensional risk assessment dimensional indicators, thereby improving the comprehensiveness and accuracy of risk assessment.

[0029] Step S2: searching and associating based on the power grid emergency repair risk assessment dimensional indicator set to determine a secondary dimensional risk assessment indicator set;

[0030] like Figure 2 As shown, further, the step of determining the secondary dimension risk assessment indicator set in this application also includes:

[0031] Based on the power grid repair risk assessment dimension indicator set, related indicator searches are performed respectively to obtain a generalized risk assessment indicator set;

[0032] After decentralizing each risk assessment indicator in the generalized risk assessment indicator set, a covariance matrix is ​​obtained;

[0033] Calculating the covariance matrix to determine the eigenvalues ​​and eigenvectors of the covariance matrix;

[0034] The risk assessment indicators are projected onto the feature vector to obtain the secondary dimensional risk assessment indicator set after the dimensionality reduction of the risk assessment indicator information.

[0035] Specifically, the search association is performed based on the set of dimensional indicators of the power grid emergency repair risk assessment, that is, all the associated secondary indicators of each dimensional indicator in the set of dimensional indicators of the power grid emergency repair risk assessment are searched separately. Among them, the power grid environment indicators in the set of dimensional indicators of the power grid emergency repair risk assessment include related indicators such as weather, geographical location, traffic conditions, and population density; the emergency repair resource indicators include related indicators such as human resources, material resources, and technical resources; the collaborative emergency repair indicators include related indicators such as internal collaboration and external collaboration; the fault risk indicators include related indicators such as fault type and severity; and the fault time risk indicators include related indicators such as fault occurrence time and duration, so as to integrate and obtain a generalized risk assessment indicator set. Then, after the risk assessment indicators in the generalized risk assessment indicator set are decentralized, each indicator is subtracted from its mean value, so that the data is centered on zero. After decentralization, the covariance matrix of the generalized risk assessment indicator set is calculated. The covariance matrix reflects the correlation and changes between the indicators, and describes the correlation and changes between the evaluation indicators in the generalized risk assessment indicator set.

[0036] Then perform eigenvalue decomposition calculation on the covariance matrix to determine the eigenvalue and eigenvector of the covariance matrix, wherein the eigenvalue represents the importance of the change direction represented by each eigenvector in the covariance matrix, and the eigenvector represents the main change direction of the covariance matrix, that is, it describes the correlation between the indicators. According to the calculated eigenvalues ​​and eigenvectors, they are sorted according to the size of the eigenvalues, and the eigenvectors with larger eigenvalues ​​are selected for retention as eigenvectors with strong correlation with the power grid repair risk. Each risk assessment indicator is projected onto the eigenvector, that is, for each risk assessment indicator information, it is multiplied by the eigenvector, and a new projection value is obtained by summing up, so that each risk assessment indicator is projected in the subspace represented by the eigenvector, and the secondary dimensional risk assessment indicator set after the dimensionality reduction of each risk assessment indicator information is obtained, and the secondary dimensional risk assessment indicator set is the power grid repair risk indicator information with strong correlation. Reduce the data processing dimension by reducing the indicator dimension, extract the risk assessment indicators with strong correlation, and then improve the data calculation efficiency.

[0037] Step S3: Building a power grid emergency repair risk assessment indicator system according to the power grid emergency repair risk assessment dimensional indicator set and the secondary dimensional risk assessment indicator set;

[0038] Furthermore, the application steps for establishing a risk assessment index system for power grid emergency repairs also include:

[0039] The power grid repair expert group performs weight evaluation on the power grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set in sequence based on the risk assessment weighting rule to obtain an initial risk indicator weight evaluation information set;

[0040] Performing deviation calculation on the initial risk indicator weight evaluation information set to obtain a risk indicator weight deviation parameter;

[0041] Re-weighting is performed according to the risk indicator weight deviation parameter until the preset deviation standard is met to obtain risk indicator weight allocation information;

[0042] Based on the power grid emergency repair risk assessment dimensional indicator set, the secondary dimensional risk assessment indicator set and the risk indicator weight distribution information, the power grid emergency repair risk assessment indicator system is established.

[0043] Furthermore, the steps of obtaining risk indicator weight allocation information in this application also include:

[0044] Re-weighting is performed according to the risk indicator weight deviation parameter until the preset deviation standard is met to obtain a risk indicator weight assignment matrix;

[0045] Marking the trustworthiness of each expert in the power grid emergency repair expert group according to the power grid emergency repair experience, and obtaining a trustworthiness set of the expert group;

[0046] Based on the trustworthiness set of the expert group, generating a trustworthiness correction matrix;

[0047] The risk indicator weight assignment matrix is ​​weighted calculated based on the trust correction matrix to determine the risk indicator weight allocation information.

[0048] Specifically, according to the grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set, a grid repair risk assessment indicator system is established. The grid repair risk assessment indicator system is a comprehensive reference system for grid repair risk assessment, which improves the professionalism and rationality of risk assessment. Specifically, first, the grid repair expert group conducts weight evaluation on the grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set in turn based on the risk assessment weighting rules, wherein the risk assessment weighting rules are the evaluation basis for the importance of risk assessment indicators, which can be set based on experience, for example, the evaluation basis includes the scope of indicator influence, the proportion of repair performance, etc.

[0049] The expert group evaluates the weight of each indicator based on the evaluation basis and obtains the initial risk indicator weight evaluation information set corresponding to each expert evaluation. Then, the deviation calculation is performed on the initial risk indicator weight evaluation information set, that is, the standard deviation of the expert weight evaluation of each risk indicator is calculated. The standard deviation indicates the degree of dispersion of the evaluation of the indicator weight by each expert, and the deviation parameter of each risk indicator weight is calculated in this way. When the risk indicator weight deviation parameter is too large, it indicates that the opinions of each expert differ too much and the weighting accuracy is not high. The result needs to be returned for the expert to re-weight until the preset deviation standard is met. The preset deviation standard is the weighting deviation benchmark, which is set according to the weighting accuracy requirements. When the benchmark is reached, it indicates that the weighting opinions of each expert tend to be unified and the weighting deviation standard is reached. The weighting results of each expert indicator that reaches the deviation standard are combined to obtain the risk indicator weight assignment matrix.

[0050] At the same time, the trustworthiness of each expert in the power grid emergency repair expert group is marked according to the power grid emergency repair experience, wherein the power grid emergency repair experience includes the expert's years of emergency repair work and the emergency repair effect, etc. The richer the emergency repair experience, the higher the trustworthiness of the expert. The trustworthiness set of the expert group is determined according to the power grid emergency repair experience level. Then, based on the trustworthiness set of the expert group, a trustworthiness correction matrix is ​​generated, and the risk indicator weight assignment matrix is ​​weighted calculated based on the trustworthiness correction matrix. The higher the trustworthiness of the expert, the greater the proportion of the corresponding final indicator weight assignment. The risk indicator weight assignment information is calculated and determined, and the risk indicator weight assignment information is the indicator weight assignment result combined with the expert emergency repair experience. Based on the power grid emergency repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set and the risk indicator weight assignment information, a power grid emergency repair risk assessment indicator system is constructed. Improve the comprehensiveness of the power grid emergency repair risk assessment indicator system, increase the professionalism and rationality of the risk assessment indicators, and thus improve the accuracy of risk assessment.

[0051] Step S4: constructing a power grid emergency repair database through data-driven collection, analyzing and training the power grid emergency repair database based on the power grid emergency repair risk assessment indicator system, and generating a power grid emergency repair risk assessment network;

[0052] Furthermore, the generation of the power grid emergency repair risk assessment network, the application steps also include:

[0053] Classifying the power grid emergency repair database based on the power grid emergency repair risk assessment index system to obtain a power grid emergency repair index sample data set;

[0054] Dividing the power grid repair indicator sample data set into a training set, a test set and a validation set according to a preset ratio;

[0055] The risk assessment model is trained based on the training set, and the risk assessment model is tested and verified based on the test set and the validation set to determine the emergency repair assessment branch network set;

[0056] The emergency repair assessment branch network set is merged according to the risk indicator weight allocation information to generate the power grid emergency repair risk assessment network.

[0057] Furthermore, the step of determining the emergency repair assessment branch network set in this application also includes:

[0058] Test and verify the risk assessment model based on the test set and validation set to obtain the model assessment accuracy;

[0059] When the model evaluation accuracy does not reach a preset accuracy threshold, configuring a model parameter optimizer;

[0060] The training model is optimized and updated based on the model parameter optimizer until a preset evaluation accuracy rate is reached, thereby obtaining the emergency repair evaluation branch network set.

[0061] Specifically, a power grid repair database is constructed through data-driven collection. Data-driven is a method that uses data as the main driving force to make decisions or optimize processes through data analysis and use. Various data related to power grid repair are collected and searched through data-driven to form a power grid repair database, which includes power grid repair element situation data and power grid repair risk data. The power grid repair database is analyzed and trained based on the power grid repair risk assessment index system, and the power grid repair database is classified based on the secondary dimensional risk assessment index set in the power grid repair risk assessment index system, that is, the database is associated and classified according to the indicator types in the indicator system, so as to obtain a classified power grid repair indicator sample data set.

[0062] The power grid repair index sample data set is divided into a training set, a test set and a validation set according to a preset ratio. For example, the sample data can be divided into a training set, a test set and a validation set according to a ratio of 7:2:1. The risk assessment model is trained based on the training set, and the risk assessment model is tested and verified based on the test set and the validation set to obtain the model assessment accuracy of each indicator risk assessment model. When the model assessment accuracy does not reach the preset accuracy threshold, it indicates that the accuracy of the risk assessment model is not enough, and the model parameter optimizer is configured. The model parameter optimizer is an algorithm for updating model parameters to minimize the training error. Common optimizer algorithms include stochastic gradient descent, Adam, etc. The choice of optimizer has a great influence on the performance and convergence speed of the model. The model parameters can be modified to control the learning rate, momentum, weight decay and optimization process, etc. For example, the sensitivity of the model to parameter updates during training can be adjusted by setting the learning rate.

[0063] According to the model requirements, a model parameter optimizer is selected to optimize and update the training model until the preset evaluation accuracy is reached, and a set of emergency repair evaluation branch networks is obtained after the accuracy reaches the standard. The emergency repair evaluation branch network set corresponds to the sample data of the secondary dimension risk assessment indicator set. Finally, the emergency repair evaluation branch network set is fused according to the risk indicator weight distribution information. The branch network with a larger risk indicator weight has a greater voting right in the final fusion model, and then the power grid emergency repair risk assessment network is generated by fusion. The power grid emergency repair risk assessment network has higher accuracy and comprehensiveness. By generating a power grid emergency repair risk assessment network, multi-dimensional indicators can be intelligently evaluated for power grid emergency repair risks, thereby improving the comprehensiveness and accuracy of power grid emergency repair risk assessment.

[0064] Step S5: Modeling the target power grid repair area using digital twin technology, and building a digital twin model of the power grid repair area;

[0065] Step S6: extracting risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment index system to obtain power grid emergency repair risk factor information;

[0066] Specifically, the target power grid repair area is modeled using digital twin technology, wherein the target power grid repair area is the power grid area to be repaired, and a digital twin model of the power grid repair area is built based on its relevant geographical location, power grid configuration information, and operating status data. The digital twin model of the power grid repair area is used to simulate the operating conditions of the target power grid repair area, visualize the power grid repair status, and thus ensure accurate decision-making for power grid repair. Risk factors are extracted from the digital twin model of the power grid repair area based on the power grid repair risk assessment index system, that is, the power grid repair situation data is extracted according to the power grid repair risk assessment index system to obtain corresponding power grid repair risk factor information, and quote power grid environment factors, repair resource factors, and fault risk factors.

[0067] Step S7: performing risk assessment and risk repair decision-making on the power grid repair risk factor information based on the power grid repair risk assessment network.

[0068] Furthermore, the risk assessment and risk repair decision-making of the power grid repair risk factor information based on the power grid repair risk assessment network, the application steps also include:

[0069] Evaluate the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network, and output a power grid emergency repair risk assessment result;

[0070] Constructing a power grid emergency repair and maintenance solution library, wherein the power grid emergency repair and maintenance solution library includes emergency repair and maintenance solutions for various types of emergency repair risks and power grid emergency repair effects;

[0071] Mapping and matching the power grid emergency repair risk assessment result with the power grid emergency repair operation and maintenance solution library to construct a power grid emergency repair operation and maintenance space;

[0072] The power grid emergency repair effect is used as a reward value to screen the power grid emergency repair operation and maintenance space, obtain a power grid risk emergency repair plan, and make a risk emergency repair decision based on the power grid risk emergency repair plan.

[0073] Specifically, based on the power grid emergency repair risk assessment network, the power grid emergency repair risk factor information is subjected to risk assessment and risk emergency repair decision making. First, the power grid emergency repair risk factor information is assessed based on the power grid emergency repair risk assessment network, and the power grid emergency repair risk assessment result is output, and the power grid emergency repair risk assessment result includes risk type and risk level. A power grid emergency repair operation and maintenance solution library is constructed, and the power grid emergency repair operation and maintenance solution library includes emergency repair operation and maintenance solutions for various types of emergency repair risks and corresponding power grid emergency repair effects. The power grid emergency repair risk assessment result is mapped and matched with the power grid emergency repair operation and maintenance solution library to obtain a set of emergency repair operation and maintenance solutions that match the risk assessment result, thereby forming a power grid emergency repair operation and maintenance space. The power grid emergency repair effect is used as a reward value to screen the power grid emergency repair operation and maintenance space, and the solution with the best power grid emergency repair effect is selected as the power grid risk emergency repair solution, and a risk emergency repair decision is made based on the power grid risk emergency repair solution. Improve the timeliness and applicability of power grid emergency repair risk decision operation and maintenance, thereby ensuring the efficiency and accuracy of emergency repair decisions.

[0074] In summary, the data-driven power grid emergency repair risk assessment method and decision-making system provided by this application have the following technical effects:

[0075] The invention adopts the method of searching and associating based on the set of risk assessment dimensions of power grid repair, determining the set of risk assessment indicators of the secondary dimension, and then building the risk assessment indicator system of power grid repair according to the set of risk assessment dimensions of power grid repair and the set of risk assessment indicators of the secondary dimension; building the power grid repair database through data-driven collection, analyzing and training the power grid repair database based on the power grid repair risk assessment indicator system, and generating the power grid repair risk assessment network; at the same time, using the digital twin technology to model the target power grid repair area, building the digital twin model of the power grid repair area, and then extracting the risk factors of the digital twin model of the power grid repair area based on the power grid repair risk assessment indicator system, and obtaining the risk factor information of power grid repair; and conducting risk assessment and risk repair decision-making on the risk factor information of power grid repair based on the power grid repair risk assessment network. Thus, the technical effect of realizing the intelligent assessment of power grid repair risk with multi-dimensional indicators, improving the comprehensiveness and accuracy of risk assessment, and thus ensuring the efficiency of repair decision-making is achieved.

[0076] Embodiment 2

[0077] Based on the same inventive concept as the data-driven power grid repair risk assessment method in the aforementioned embodiment, the present invention also provides a data-driven power grid repair risk decision-making system, such as Figure 3 As shown, the system comprises:

[0078] The risk assessment dimension indicator acquisition module 11 is used to acquire a set of dimension indicators for power grid emergency repair risk assessment, wherein the set of dimension indicators for power grid emergency repair risk assessment includes power grid environment, emergency repair resources, collaborative emergency repair, fault risk, and fault time risk;

[0079] An indicator search and association module 12 is used to search and associate based on the power grid emergency repair risk assessment dimension indicator set to determine a secondary dimension risk assessment indicator set;

[0080] A risk assessment indicator system building module 13 is used to build a power grid emergency repair risk assessment indicator system according to the power grid emergency repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set;

[0081] A power grid repair risk assessment network generation module 14 is used to construct a power grid repair database through data-driven collection, analyze and train the power grid repair database based on the power grid repair risk assessment indicator system, and generate a power grid repair risk assessment network;

[0082] A digital twin model building module 15 is used to model the target power grid repair area using digital twin technology and build a digital twin model of the power grid repair area;

[0083] A risk factor extraction module 16 is used to extract risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment index system to obtain power grid emergency repair risk factor information;

[0084] The risk assessment decision module 17 is used to perform risk assessment and risk emergency repair decision on the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network.

[0085] Furthermore, the system also includes:

[0086] A correlation indicator search unit, used to search for correlation indicators based on the power grid emergency repair risk assessment dimension indicator set to obtain a generalized risk assessment indicator set;

[0087] A decentralized processing unit, configured to obtain a covariance matrix after decentralized processing of each risk assessment indicator in the generalized risk assessment indicator set;

[0088] A covariance matrix calculation unit, used to calculate the covariance matrix and determine the eigenvalues ​​and eigenvectors of the covariance matrix;

[0089] The indicator dimension reduction unit is used to project the risk assessment indicators onto the feature vector to obtain the secondary dimensional risk assessment indicator set after the dimension reduction of the risk assessment indicator information.

[0090] Furthermore, the system also includes:

[0091] An indicator weight evaluation unit is used for the power grid repair expert group to perform weight evaluation on the power grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set in sequence based on the risk assessment weighting rule to obtain an initial risk indicator weight evaluation information set;

[0092] A weight deviation calculation unit, used to perform deviation calculation on the initial risk indicator weight evaluation information set to obtain a risk indicator weight deviation parameter;

[0093] An indicator weight allocation information obtaining unit, used to re-weight according to the risk indicator weight deviation parameter until a preset deviation standard is met, and obtain risk indicator weight allocation information;

[0094] An evaluation index system building unit is used to build the power grid emergency repair risk assessment index system based on the power grid emergency repair risk assessment dimension index set, the secondary dimension risk assessment index set and the risk index weight distribution information.

[0095] Furthermore, the system also includes:

[0096] A weight assignment matrix obtaining unit is used to re-weight according to the risk indicator weight deviation parameter until a preset deviation standard is met to obtain a risk indicator weight assignment matrix;

[0097] A trustworthiness marking unit, used to mark the trustworthiness of each expert in the power grid emergency repair expert group according to the power grid emergency repair experience, and obtain a trustworthiness set of the expert group;

[0098] A trust correction matrix generating unit, used for generating a trust correction matrix based on the trustworthiness set of the expert group;

[0099] A weighted calculation unit is used to perform weighted calculation on the risk indicator weight assignment matrix based on the trust correction matrix to determine the risk indicator weight allocation information.

[0100] Furthermore, the system also includes:

[0101] A database classification unit, used to classify the power grid emergency repair database based on the power grid emergency repair risk assessment index system to obtain a power grid emergency repair index sample data set;

[0102] A sample data set division unit, used to divide the power grid repair indicator sample data set into a training set, a test set and a validation set according to a preset ratio;

[0103] An assessment model training unit is used to train the risk assessment model based on the training set, and to test and verify the risk assessment model based on the test set and the verification set, so as to determine a set of emergency repair assessment branch networks;

[0104] The branch network fusion unit is used to fuse the emergency repair assessment branch network set according to the risk indicator weight allocation information to generate the power grid emergency repair risk assessment network.

[0105] Furthermore, the system also includes:

[0106] Model testing and verification unit, used to test and verify the risk assessment model based on the test set and verification set to obtain the model assessment accuracy;

[0107] A parameter optimizer configuration unit, configured to configure a model parameter optimizer when the model evaluation accuracy does not reach a preset accuracy threshold;

[0108] The branch network set obtaining unit is used to optimize and update the training model based on the model parameter optimizer until the preset evaluation accuracy is reached to obtain the emergency repair evaluation branch network set.

[0109] Furthermore, the system also includes:

[0110] A risk assessment result output unit, used to evaluate the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network, and output a power grid emergency repair risk assessment result;

[0111] A repair and maintenance solution library construction unit is used to construct a power grid repair and maintenance solution library, wherein the power grid repair and maintenance solution library includes repair and maintenance solutions for various types of repair risks and power grid repair effects;

[0112] A scheme mapping and matching unit, used for mapping and matching the power grid emergency repair risk assessment result with the power grid emergency repair and operation and maintenance scheme library to construct a power grid emergency repair and operation and maintenance space;

[0113] The risk emergency repair decision unit is used to screen the power grid emergency repair operation and maintenance space by taking the power grid emergency repair effect as a reward value, obtain a power grid risk emergency repair plan, and make a risk emergency repair decision based on the power grid risk emergency repair plan.

[0114] The foregoing Figure 1 The various variations and specific examples of the data-driven power grid emergency repair risk assessment method in Example 1 are also applicable to the data-driven power grid emergency repair risk decision-making system in this embodiment. Through the above detailed description of the data-driven power grid emergency repair risk assessment method, technical personnel in this field can clearly understand the implementation method of the data-driven power grid emergency repair risk decision-making system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0115] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and run on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method embodiment for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0116] Exemplary Electronic Devices

[0117] For details, see Figure 4 As shown, the present application also provides an electronic device, which includes a bus 1110 , a processor 1120 , a transceiver 1130 , a bus interface 1140 , a memory 1150 and a user interface 1160 .

[0118] In the present application, the electronic device further includes: a computer program stored in the memory 1150 and executable on the processor 1120, and when the computer program is executed by the processor 1120, each process of the above-mentioned method embodiment for controlling output data is implemented.

[0119] The transceiver 1130 is configured to receive and send data under the control of the processor 1120 .

[0120] In the present application, a bus architecture (represented by bus 1110 ) may include any number of interconnected buses and bridges, and bus 1110 connects various circuits including one or more processors represented by processor 1120 and a memory represented by memory 1150 .

[0121] Bus 1110 represents one or more of any of several types of bus structures, including a memory bus and memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. Such architectures include, by way of example and not limitation, an Industry Standard Architecture bus, a Micro Channel Architecture bus, an expansion bus, a Video Electronics Standards Association, a Peripheral Component Interconnect bus.

[0122] The processor 1120 may be an integrated circuit chip having signal processing capabilities. In the implementation process, each step of the above method embodiment may be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processors include: a general-purpose processor, a central processing unit, a network processor, a digital signal processor, an application-specific integrated circuit, a field programmable gate array, a complex programmable logic device, a programmable logic array, a microcontroller unit or other programmable logic device, a discrete gate, a transistor logic device, and a discrete hardware component. The various methods, steps, and logic block diagrams disclosed in this application may be implemented or executed. For example, the processor may be a single-core processor or a multi-core processor, and the processor may be integrated into a single chip or located on multiple different chips.

[0123] Processor 1120 may be a microprocessor or any conventional processor. The method steps disclosed in the present application may be directly executed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a readable storage medium known in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, a register, etc. The readable storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0124] The bus 1110 may also connect various other circuits such as peripheral devices, voltage regulators or power management circuits, and the bus interface 1140 provides an interface between the bus 1110 and the transceiver 1130, which are well known in the art. Therefore, this application will not further describe them.

[0125] The transceiver 1130 may be one element or multiple elements, such as multiple receivers and transmitters, and provides a unit for communicating with various other devices on a transmission medium. For example, the transceiver 1130 receives external data from other devices, and the transceiver 1130 is used to send data processed by the processor 1120 to other devices. Depending on the nature of the computer device, a user interface 1160 may also be provided, such as a touch screen, a physical keyboard, a display, a mouse, a speaker, a microphone, a trackball, a joystick, or a stylus.

[0126] It should be understood that in the present application, the memory 1150 may further include a memory remotely arranged relative to the processor 1120, and these remotely arranged memories may be connected to the server through a network. One or more parts of the above network may be a self-organizing network, an intranet, an extranet, a virtual private network, a local area network, a wireless local area network, a wide area network, a wireless wide area network, a metropolitan area network, the Internet, a public switched telephone network, a plain old telephone service network, a cellular telephone network, a wireless network, a wireless fidelity network, and a combination of two or more of the above networks. For example, the cellular telephone network and the wireless network may be a global mobile communication device, a code division multiple access device, a global microwave interconnection access device, a general packet radio service device, a wideband code division multiple access device, a long term evolution device, a LTE frequency division duplex device, a LTE time division duplex device, an advanced long term evolution device, a universal mobile communication device, an enhanced mobile broadband device, a massive machine type communication device, an ultra-reliable low latency communication device, and the like.

[0127] It should be understood that the memory 1150 in the present application may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. Among them, the non-volatile memory includes: a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, or a flash memory.

[0128] Volatile memory includes random access memory, which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory, dynamic random access memory, synchronous dynamic random access memory, double data rate synchronous dynamic random access memory, enhanced synchronous dynamic random access memory, synchronously linked dynamic random access memory, and direct memory bus random access memory. The memory 1150 of the electronic device described in the present application includes, but is not limited to, the above and any other suitable types of memory.

[0129] In the present application, the memory 1150 stores the following elements of the operating system 1151 and the application program 1152: executable modules, data structures, or subsets thereof, or extended sets thereof.

[0130] Specifically, the operating system 1151 includes various device programs, such as a framework layer, a core library layer, a driver layer, etc., which are used to implement various basic services and process hardware-based tasks. The application 1152 includes various application programs, such as a media player and a browser, which are used to implement various application services. The program implementing the method of the present application may be included in the application 1152. The application 1152 includes applets, objects, components, logic, data structures, and other computer device executable instructions that perform specific tasks or implement specific abstract data types.

[0131] In addition, the present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the various processes of the above-mentioned method embodiment for controlling output data are implemented and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0132] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data-driven power grid repair risk assessment method, characterized in that: The method is applied to a power grid emergency repair risk decision-making system, and the method comprises: Obtaining a set of dimensional indicators for power grid emergency repair risk assessment, wherein the set of dimensional indicators for power grid emergency repair risk assessment includes power grid environment, emergency repair resources, collaborative emergency repair, fault risk, and fault time risk; Based on the power grid emergency repair risk assessment dimension indicator set, search and associate to determine the secondary dimension risk assessment indicator set; Building a power grid emergency repair risk assessment indicator system according to the power grid emergency repair risk assessment dimensional indicator set and the secondary dimensional risk assessment indicator set; Building a power grid emergency repair database through data-driven collection, analyzing and training the power grid emergency repair database based on the power grid emergency repair risk assessment index system, and generating a power grid emergency repair risk assessment network; Use digital twin technology to model the target power grid repair area and build a digital twin model of the power grid repair area; Based on the power grid emergency repair risk assessment index system, risk factors are extracted from the digital twin model of the power grid emergency repair area to obtain power grid emergency repair risk factor information; Based on the power grid emergency repair risk assessment network, risk assessment and risk emergency repair decision-making are performed on the power grid emergency repair risk factor information; The establishment of a power grid emergency repair risk assessment indicator system includes: The power grid repair expert group performs weight evaluation on the power grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set in sequence based on the risk assessment weighting rule to obtain an initial risk indicator weight evaluation information set; Performing deviation calculation on the initial risk indicator weight evaluation information set to obtain a risk indicator weight deviation parameter; Re-weighting is performed according to the risk indicator weight deviation parameter until the preset deviation standard is met to obtain risk indicator weight allocation information; Based on the power grid emergency repair risk assessment dimensional indicator set, the secondary dimensional risk assessment indicator set and the risk indicator weight allocation information, building the power grid emergency repair risk assessment indicator system; The generating network for power grid emergency repair risk assessment comprises: Classifying the power grid emergency repair database based on the power grid emergency repair risk assessment index system to obtain a power grid emergency repair index sample data set; Dividing the power grid repair indicator sample data set into a training set, a test set and a validation set according to a preset ratio; The risk assessment model is trained based on the training set, and the risk assessment model is tested and verified based on the test set and the validation set to determine the emergency repair assessment branch network set; The emergency repair assessment branch network set is merged according to the risk indicator weight allocation information to generate the power grid emergency repair risk assessment network.

2. The method according to claim 1, characterized in that The step of determining a set of secondary dimension risk assessment indicators includes: Based on the power grid repair risk assessment dimension indicator set, related indicator searches are performed respectively to obtain a generalized risk assessment indicator set; After decentralizing each risk assessment indicator in the generalized risk assessment indicator set, a covariance matrix is ​​obtained; Calculating the covariance matrix to determine the eigenvalues ​​and eigenvectors of the covariance matrix; The risk assessment indicators are projected onto the feature vector to obtain the secondary dimensional risk assessment indicator set after the dimensionality reduction of the risk assessment indicator information.

3. The method according to claim 1, characterized in that The obtaining of risk indicator weight allocation information includes: Re-weighting is performed according to the risk indicator weight deviation parameter until the preset deviation standard is met to obtain a risk indicator weight assignment matrix; Marking the trustworthiness of each expert in the power grid emergency repair expert group according to the power grid emergency repair experience, and obtaining a trustworthiness set of the expert group; Based on the trustworthiness set of the expert group, generating a trustworthiness correction matrix; The risk indicator weight assignment matrix is ​​weighted calculated based on the trust correction matrix to determine the risk indicator weight allocation information.

4. The method according to claim 1, characterized in that The step of determining a set of emergency repair assessment branch networks includes: Test and verify the risk assessment model based on the test set and validation set to obtain the model assessment accuracy; When the model evaluation accuracy does not reach a preset accuracy threshold, configuring a model parameter optimizer; The training model is optimized and updated based on the model parameter optimizer until a preset evaluation accuracy rate is reached, thereby obtaining the emergency repair evaluation branch network set.

5. The method according to claim 1, characterized in that The risk assessment and risk repair decision-making based on the power grid repair risk assessment network for the power grid repair risk factor information includes: Evaluate the power grid emergency repair risk factor information based on the power grid emergency repair risk assessment network, and output a power grid emergency repair risk assessment result; Constructing a power grid emergency repair and maintenance solution library, wherein the power grid emergency repair and maintenance solution library includes emergency repair and maintenance solutions for various types of emergency repair risks and power grid emergency repair effects; Mapping and matching the power grid emergency repair risk assessment result with the power grid emergency repair operation and maintenance solution library to construct a power grid emergency repair operation and maintenance space; The power grid emergency repair effect is used as a reward value to screen the power grid emergency repair operation and maintenance space, obtain a power grid risk emergency repair plan, and make a risk emergency repair decision based on the power grid risk emergency repair plan.

6. A data-driven power grid emergency repair risk decision-making system, characterized by: The system comprises: A risk assessment dimension indicator acquisition module is used to acquire a set of grid repair risk assessment dimension indicators, wherein the grid repair risk assessment dimension indicator set includes grid environment, repair resources, collaborative repair, fault risk, and fault time risk; An indicator search and association module, used to search and associate based on the power grid emergency repair risk assessment dimension indicator set to determine a secondary dimension risk assessment indicator set; A risk assessment indicator system building module, used to build a power grid emergency repair risk assessment indicator system according to the power grid emergency repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set; A power grid repair risk assessment network generation module is used to construct a power grid repair database through data-driven collection, analyze and train the power grid repair database based on the power grid repair risk assessment indicator system, and generate a power grid repair risk assessment network; A digital twin model building module is used to model the target power grid repair area using digital twin technology and build a digital twin model of the power grid repair area; A risk factor extraction module is used to extract risk factors from the digital twin model of the power grid emergency repair area based on the power grid emergency repair risk assessment index system to obtain power grid emergency repair risk factor information; A risk assessment decision module, used for performing risk assessment and risk repair decision on the power grid repair risk factor information based on the power grid repair risk assessment network; An indicator weight evaluation unit is used for the power grid repair expert group to perform weight evaluation on the power grid repair risk assessment dimension indicator set and the secondary dimension risk assessment indicator set in sequence based on the risk assessment weighting rule to obtain an initial risk indicator weight evaluation information set; A weight deviation calculation unit, used to perform deviation calculation on the initial risk indicator weight evaluation information set to obtain a risk indicator weight deviation parameter; An indicator weight allocation information obtaining unit, used to re-weight according to the risk indicator weight deviation parameter until a preset deviation standard is met, and obtain risk indicator weight allocation information; An evaluation indicator system building unit, used to build the power grid emergency repair risk assessment indicator system based on the power grid emergency repair risk assessment dimension indicator set, the secondary dimension risk assessment indicator set and the risk indicator weight allocation information; A database classification unit, used to classify the power grid emergency repair database based on the power grid emergency repair risk assessment index system to obtain a power grid emergency repair index sample data set; A sample data set division unit, used to divide the power grid repair indicator sample data set into a training set, a test set and a validation set according to a preset ratio; An assessment model training unit is used to train the risk assessment model based on the training set, and to test and verify the risk assessment model based on the test set and the verification set, so as to determine a set of emergency repair assessment branch networks; The branch network fusion unit is used to fuse the emergency repair assessment branch network set according to the risk indicator weight allocation information to generate the power grid emergency repair risk assessment network.

7. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the data-driven power grid emergency repair risk assessment method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in the data-driven power grid emergency repair risk assessment method as described in any one of claims 1 to 5 are implemented.

Images