Dynamic reference risk management method and system

Abstract

The invention discloses a reference risk dynamic management method and system, and relates to the technical field of power grid risk dynamic management, and the method comprises the steps: collecting zero-power user data, and building a first station line transformer user relation model; establishing first dynamic monitoring; key equipment in the power grid and the risk level of the power grid after a fault are automatically identified according to real-time operation data, and a reference risk report is updated in a rolling mode. According to the method, automatic collection and integration of zero electric quantity user data and linkage analysis of a power grid equipment and user risk relation are realized by establishing the first station line transformer user relation model, and the operation state change of the power grid is displayed in real time by establishing the first dynamic monitoring system, so that the operation efficiency of the power grid is improved. According to the technical scheme, a power grid manager can clearly master real-time data, key equipment in the power grid can be automatically identified through analysis of the real-time operation data, and therefore rapid positioning of a power-losing area is achieved, the identification speed and accuracy are improved, the requirement for manual intervention is reduced, and high efficiency of risk assessment is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of dynamic management of power grid risks, and in particular to a method and system for dynamic management of benchmark risks. Background Art

[0002] With the acceleration of urbanization and the rapid expansion of the power grid, the complexity and uncertainty of the power system are also increasing, especially in the risk management of the power grid. The traditional power grid risk control system has gradually exposed many deficiencies in the face of a rapidly changing market environment and increasing load pressure. First, in terms of user data changes, due to the uncertainty of the number of zero-power users and new users of business expansion, the results of power grid risk assessment are easily distorted. The rapid changes in zero-power user data make the real-time performance of power grid risk assessment a huge challenge. Existing assessment tools cannot be dynamically updated and provide intuitive and comprehensive data analysis. This lack of timeliness and accuracy in analysis means makes it impossible for risk management to be dynamically and comprehensively monitored, which in turn leads to the failure to timely discover and handle potential risk events. For example, the growth of zero-power users may imply a reduction in the number of users and a reduction in the risk of power grid operation, but traditional analysis methods are difficult to capture and evaluate these phenomena in a timely manner.

[0003] Secondly, with the increase in the number of substations and the growth in the number of users, the complex multi-level and multi-dimensional status of the power grid makes it difficult to perceive and control the dynamic changes of baseline risks. Traditional risk assessment methods often lack the technical support of diversified assessments and cannot effectively adapt to the changes brought about by business expansion and equipment commissioning. This multi-dimensional and volatile risk situation requires a technical means that can be dynamically adapted and widely covered to improve the accuracy and efficiency of risk assessment.

[0004] Finally, risk assessment and identification work is still mainly carried out manually, which not only consumes a lot of human resources, but also takes a long time and is inefficient. Relying on manual risk identification and management may not only lead to human errors, but also make it difficult to meet real-time requirements. This traditional manual method is not compatible with the rapid development of modern power systems, and more intelligent and automated solutions are urgently needed to improve work efficiency and effectiveness. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is: the existing power grid risk assessment method has the problems of untimely processing of zero-power user data, reliance on manual risk identification and assessment, insufficient dynamic risk perception capability, and how to realize automated risk assessment and dynamic perception based on real-time user data in the power grid.

[0007] To solve the above technical problems, the present invention provides the following technical solutions: a baseline risk dynamic management method, comprising collecting zero-power user data and establishing a first station-line-user relationship model; establishing a first dynamic monitoring; automatically identifying key equipment in the power grid and the risk level of the power grid after a fault based on real-time operating data, and rolling updating the baseline risk report.

[0008] As a preferred solution of the benchmark risk dynamic management method described in the present invention, the collection of zero-power user data includes fusing the zero-power user data with the distribution transformer user data.

[0009] As a preferred solution of the benchmark risk dynamic management method described in the present invention, wherein: the first station-line-user relationship model includes a linkage analysis of the risk relationship between equipment and users.

[0010] As a preferred solution of the baseline risk dynamic management method described in the present invention, the first dynamic monitoring includes displaying changes in the operating status of the power grid.

[0011] As a preferred solution of the benchmark risk dynamic management method described in the present invention, wherein: the first dynamic monitoring also includes risk identification based on the first station line change customer relationship model.

[0012] As a preferred solution of the benchmark risk dynamic management method described in the present invention, the automatic identification of key equipment in the power grid includes topology deduction based on N-1 and N-2 analysis methods to automatically identify key equipment in the power outage area; and comprehensive topology scanning and calculation are performed through breadth-first search and depth-first search algorithms.

[0013] As a preferred scheme of the benchmark risk dynamic management method described in the present invention, wherein: the rolling update of the benchmark risk report includes setting up faulty equipment, superimposing normal operating modes to identify risks, calculating the key equipment on the link, and based on the key equipment, conducting risk assessment from five dimensions: load reduction, pressure loss plant, number of affected users, proportion of load loss, and proportion of number of lost users, calculating risk scores, and finally listing the accident or event levels to generate a benchmark risk list.

[0014] Another object of the present invention is to provide a benchmark risk dynamic management system, which can collect data on zero-electricity users in the power grid, integrate zero-electricity users with the number of distribution transformer users, and construct a first-station line-transformer-user relationship model, thereby solving the problem of untimely processing of zero-electricity user data in current power grid risk assessment methods.

[0015] As a preferred solution of the benchmark risk dynamic management system described in the present invention, it includes: a model building module, a dynamic monitoring module, and a risk analysis module; the model building module is used to collect data on zero-electricity users in the power grid, and integrate the zero-electricity users with the number of distribution transformer users to build a first-station line-transformer-user relationship model; the dynamic monitoring module is used to establish dynamic monitoring, display changes in the power grid operation status, and through the risk identification function based on the first-station line-transformer-user relationship model, real-time identify and evaluate the risks in the power grid operation; the risk analysis module is used to automatically identify key equipment in the power grid and the risk level of the power grid after a fault, and rollingly update the benchmark risk report.

[0016] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a step of a benchmark risk dynamic management method.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a baseline risk dynamic management method.

[0018] Beneficial effects of the invention: The benchmark risk dynamic management method provided by the invention collects zero-power user data and establishes the first station-line-user relationship model, thereby realizing the automatic collection and integration of zero-power user data and the linkage analysis of the risk relationship between power grid equipment and users. By establishing the first station-line-user relationship model, not only a comprehensive risk management framework is constructed in theory, but also practical guidance is provided for actual operation. When the risk relationship is clarified through the model, the power company can more effectively optimize scheduling and resource allocation, greatly improve the speed of responding to emergencies, and ultimately achieve the goal of reducing risks and ensuring power supply safety. By constructing the first dynamic monitoring system, the changes in the operating status of the power grid are displayed in real time, so that the power grid Managers can clearly grasp real-time data. Through the analysis of real-time operation data and the use of N-1 and N-2 analysis methods for topology deduction, they can automatically identify key equipment in the power grid, thereby realizing rapid positioning of power outage areas. This not only improves the speed and accuracy of identification, but also reduces the need for manual intervention, ensuring the efficiency of risk assessment. By rolling updates of baseline risk reports, managers can fully understand the current status of the power grid, including dimensions such as load reduction, power plant stations with pressure loss, and the number of affected users. The data analysis of the report provides a quantitative method that allows power managers to intuitively see potential risks and take preventive measures in a timely manner. The present invention achieves better results in terms of efficiency, adaptability, and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0020] Figure 1 An overall flow chart of a baseline risk dynamic management method provided for the first embodiment of the present invention.

[0021] Figure 2 A first-stop line account change model diagram of a benchmark risk dynamic management method provided in the first embodiment of the present invention.

[0022] Figure 3 A risk identification and assessment diagram of a baseline risk dynamic management method provided in the first embodiment of the present invention.

[0023] Figure 4 A schematic diagram of modules of a benchmark risk dynamic management system provided for the third embodiment of the present invention. DETAILED DESCRIPTION

[0024] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0025] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a baseline risk dynamic management method, comprising:

[0026] S1: Collect zero-electricity user data and establish the first-station line-change user relationship model.

[0027] Furthermore, collecting data on zero-electricity users includes integrating zero-electricity users with the number of users of each distribution transformer. Zero-electricity users can directly use the zero-electricity user report provided by the marketing department every month, which can be extracted, analyzed and imported through RPA technology. After importing, the zero-electricity users can be integrated with information such as the number of users of each distribution transformer.

[0028] It should be noted that the first-stop line-change user relationship model includes a linkage analysis of the risk relationship between equipment and users. There are many ways to establish the first-stop line-change user relationship model, such as building a model based on knowledge graphs and speech recognition technology or building a model based on machine learning and artificial intelligence reasoning and prediction.

[0029] As a preferred embodiment, in this embodiment, the first station line change user relationship model is established by building a model based on knowledge graph and speech recognition technology, and its principle steps are as follows:

[0030] First, RPA technology is used to automatically extract data from the zero-power user reports provided by the marketing department. These data are often discrete and heterogeneous, making them difficult to apply directly. Therefore, intelligent technologies such as knowledge graphs and semantic recognition are needed to fuse the data.

[0031] Next, in terms of knowledge graph relational model construction, based on CIM (Common Information Model), the power grid connection diagram, plant wiring diagram, and geographic information diagram are converted into a knowledge graph relational model, such as Figure 2 As shown in the figure, based on the topology splicing of the CIM model, the station diagram and the power grid connection diagram are spliced ​​to form a power supply path from the equipment in the station to the load user, forming basic information, and forming a clear tree structure through links between different voltage levels (from 10kV to 500kV). At the same time, the key indicators that affect the risk assessment are digitized, and these indicators are connected with the users and equipment in the topology to form a linkage relationship between risks and key equipment and users. By comparing the risk levels horizontally, a comprehensive risk level assessment is finally formed.

[0032] Knowledge graphs are used to describe in a structured manner the complex relationships between concepts (such as controllers and linemen), entities (such as actual power stations), and events (such as fault handling and maintenance activities) in the power grid. By integrating the basic information and operating data of the power grid, optimizing the fusion of dispatching knowledge, and realizing online analysis and auxiliary decision support, it can efficiently analyze risks, anomalies, faults, voltage, and load.

[0033] In the process of semantic recognition and information unification, the structured and unstructured information involved in the dispatching operation risks is converted into a structured risk relationship model through semantic recognition technology. In this process, the unstructured data is preprocessed through tools such as power dictionary and stop word list, and vectorized using NLP technology. At the same time, labeled event samples are extracted from historical information to enhance the diversity and comprehensiveness of the sample library, and these samples are used to train and optimize machine learning models.

[0034] Finally, with the constructed sample library, the model is trained and its recognition effect is evaluated. The model performance is optimized by using indicators such as accuracy, precision and recall. In the online application stage, the results recognized by the model are automatically pushed. If the results cannot be obtained automatically, the sample library is further improved through manual correction. This dynamic learning and updating mechanism can continuously improve the recognition accuracy and robustness of the model.

[0035] It should be noted that in another feasible embodiment, the first station line change user relationship model is established by building a model based on machine learning and artificial intelligence reasoning prediction, and its principle steps are as follows:

[0036] First, collect raw data from the historical operation data of the power grid, equipment failure records, user power consumption changes and environmental data. This is the basis for ensuring that the model fully understands the historical risk situation. In the data preprocessing stage, use data cleaning technology to eliminate noise, fill missing values ​​and correct outliers. In addition, standardize various data sources to ensure the consistency and integrity of the data format. Secondly, in the feature extraction and selection process, it is necessary to identify and extract key features such as equipment operating current, voltage, historical failure frequency, and user power consumption changes based on the specific operating characteristics of the power grid and the clear goals of risk assessment. In order to ensure that the model is efficient and suitable for practical applications, feature selection uses the principal component analysis algorithm to reduce data dimensions. Next, in the model training and optimization process, apply deep learning or ensemble learning algorithms (such as random forest and XGBoost) To carry out modeling, these extracted features are used to create model predictions for historical risk events. In order to improve the prediction accuracy of the model, the model performance is optimized through cross-validation and adjustment of hyperparameters. Subsequently, the model will be applied to real-time data analysis for intelligent reasoning and risk prediction, and to identify possible risk scenarios, such as pressure loss or equipment failure in user groups. By comparing the similarities between real-time data and historical data, the model dynamically adjusts the risk prediction results. In the risk assessment and decision support stage, a quantitative risk assessment is provided based on the prediction results, a detailed risk report is generated, and a comprehensive analysis is conducted in combination with historical data and management strategies. Practical optimization suggestions are put forward to provide strong decision support for power dispatching and operation and maintenance. This process makes risk prediction more accurate through detailed data support and intelligent algorithm processing, providing a strong guarantee for the stable operation of the power grid.

[0037] S2: Establish the first dynamic monitoring.

[0038] Furthermore, the first dynamic monitoring includes displaying the changes in the grid operation status and performing risk identification based on the first station-line-user relationship model.

[0039] It should be noted that there may be multiple methods for establishing the first dynamic monitoring, such as methods based on SVG graphs or based on Internet of Things (IoT) technology.

[0040] As a preferred embodiment, in this embodiment, the first dynamic monitoring is established based on the SVG graph, and the principle steps are as follows:

[0041] The grid status is displayed through the interaction of SVG graphics and graphics elements, and real-time updating and maintenance are supported. Specifically, key equipment graphics elements such as switches and circuit breakers are accurately identified and events are assigned, and the real-time status is conveyed through the color change, shape reshaping and text labeling of the graphics elements. For example, when a user clicks on a switch graphic element, a pop-up box will display the current current value, voltage parameters and status (such as open or closed) of the switch. This status information is provided in real time by the actual equipment data acquisition system and is immediately reflected in the SVG graphics. When the user drags the circuit breaker graphic element to a specific position, the system will simulate the operation of the circuit breaker and feedback whether it is successfully closed or opened. The graphic element status is fed back and updated synchronously based on the real-time control signal to ensure that the visual performance is highly consistent with the actual function. When the actual equipment status changes, the corresponding SVG graphic element will be updated in real time to intuitively reflect the current status of the power grid system, greatly facilitating monitoring and management.

[0042] It should be noted that in another feasible embodiment, the first dynamic monitoring is established based on the Internet of Things (IoT) technology, and the principle steps are as follows:

[0043] By deploying sensors and smart devices distributed at various key nodes of the power grid, real-time monitoring and data collection of the power grid operation status can be achieved, thereby supporting status visualization and risk assessment. Specifically, the system will install a variety of sensors on power facilities (such as substations, distribution cabinets and transmission lines, etc.), including current sensors, voltage sensors, temperature sensors and vibration sensors. These sensors can collect the operation data of the equipment in real time and transmit the data to a centralized data platform via a wireless network. The platform uses big data analysis and machine learning algorithms to process and analyze the collected real-time data to identify abnormal conditions and potential risks in equipment operation. For example, the system can monitor the equipment's temperature abnormalities, load overloads and other conditions in real time, and make predictions based on historical data to identify possible faulty nodes.

[0044] In terms of data visualization, users can access these real-time data through a dedicated monitoring interface, which presents the operating status of the power grid in a graphical manner, including information such as current, voltage and temperature of each distribution network, greatly facilitating managers to monitor and evaluate the health of the power grid.

[0045] S3: Automatically identify key equipment in the power grid and the risk level of the power grid after failure based on real-time operation data, and update the baseline risk report on a rolling basis.

[0046] Furthermore, automatic identification of key equipment in the power grid includes topology deduction based on N-1 and N-2 analysis methods, automatic identification of key equipment in power-off areas; and comprehensive topology scanning and calculation through breadth-first search and depth-first search algorithms.

[0047] Through the first station line change user relationship model and the first dynamic monitoring, such as Figure 2 As shown, combined with the normal operation mode of the first dynamic monitoring grid, according to the risk level assessment calculation, the result of the comparison of the voltage-loss substation, the loss load, and the number of lost users is formed, and the knowledge graph in the first station-line-substation-user relationship model provides the linkage relationship from grid risk to equipment and users. Then, based on the N-1 and N-2 topology deduction of the grid topology, the topology analysis is carried out from the line switch as the starting point. Through the equipment association relationship, the topology analysis is carried out according to the power outflow direction, and the bus, main transformer, switch, line and other equipment on the power supply path are obtained in turn. Then, according to the faulty equipment, standby automatic switching, power station voltage loss, etc., the key equipment that causes power loss after N-1 or N-2 is automatically analyzed. The topology scanning method adopts breadth-first search and depth-first search, and is combined with the flow information for deduction and calculation. The traversal is relatively comprehensive and has a high degree of accommodation.

[0048] It should be noted that the generation of a baseline risk report includes: Figure 3 As shown, by setting faulty equipment, such as common single-line, single-transformer, single-bus N-1, N-2 anticipated faults and complex faults of whole-station pressure loss, and superimposing the normal operation mode for risk identification, the key equipment on the link is calculated, and based on the key equipment, risk assessment is conducted from five dimensions: load reduction, pressure loss plant, number of users affected, proportion of load loss, and proportion of number of users lost. The risk score is calculated, and finally the accident or event levels are listed to generate a benchmark risk list.

[0049] It should also be noted that the first station-line-change-user relationship model has opened up the linkage relationship between risks, equipment and users. When the first dynamic monitoring and identification generates risk scenarios, the first station-line-change-user relationship model is used and ultimately reflected on key equipment with risks. Key equipment is connected to branch plants and stations through the power grid topology and is associated with users. At the same time, the load situation can be monitored and ultimately focused on key equipment. The load loss, pressure loss plant or station, or number of households during power outages affected by key equipment are calculated for online risk assessment, eliminating the need for complex manual analysis and calculations.

[0050] Example 2 is an embodiment of the present invention, which provides a benchmark risk dynamic management method. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0051] In order to verify the effectiveness of the first station-line-user relationship model and the first dynamic monitoring system, a series of experiments were carried out to systematically analyze the methods of collecting and processing zero-power user data and grid risk assessment, and focus on their innovation and implementation effects. This application takes the grid of a certain power company as an example, and the implementation process is as follows:

[0052] First, RPA technology was used to extract data from the zero-power user report provided by the power company's marketing department. The automated process ensured the efficiency of data collection. During the collection process, the relevant information of zero-power users (such as user ID, location, historical electricity consumption data, etc.) was integrated with the data of each distribution transformer user to form a comprehensive user data set. The data set includes approximately 5,000 zero-power users and approximately 20,000 distribution transformer users. The data was cleaned and structured using intelligent technology. Finally, the first station-line-transformer-user relationship model based on the CIM model was constructed using the knowledge graph. The model displays the power grid's contact diagram, plant-station wiring diagram, and geographic information map, forming a clear power supply path from power grid equipment to each load user.

[0053] Next, in the first dynamic monitoring, the real-time status of the power grid is presented by using SVG graphics technology, and the status of related graphics elements (such as switches, circuit breakers, etc.) is updated in real time through user interaction. For example, after the user clicks the switch, a pop-up window displays the current current, voltage and other information. During the implementation process, the system successfully simulated 300 operations, of which 95% of the operations were able to respond quickly and accurately update the status.

[0054] In terms of monitoring and risk assessment of power grid operation data, the system automatically identifies key equipment in the power-off area and predicts the risks that may lead to power outages by using N-1 and N-2 analysis methods combined with breadth-first search and depth-first search algorithms. In this way, the risk assessment cycle of the entire power grid is shortened to 60% of the original. When comparing the data before and after implementation, it is found that when dealing with complex faults (such as single-line, single-transformer N-1 faults), the system can quickly generate a baseline risk report, identify affected users and equipment in advance, and provide key decision-making support for subsequent emergency repairs.

[0055] Refer to Table 1 for a comparative analysis of the experimental data.

[0056] Table 1 Experimental data record table

[0057]

[0058]

[0059] Through the comparative analysis of the data in Table 1, we can clearly see the innovation and advantages of this application. First, during the implementation process, the integrated numbers of zero-power users and distribution transformer users reached 5,000 and 20,000 respectively. The richness of the data provides a solid foundation for risk analysis. Through highly automated data extraction and analysis processes, the risk assessment time is significantly shortened. For example, the overall risk assessment time is within 10 minutes on average, which is about 40% more efficient than the existing technologies on the market. This process shows that the present invention utilizes the integration advantages of RPA technology and knowledge graphs to promote real-time monitoring and risk identification of power grid operation status.

[0060] By comparing the number of key devices identified by the N-1 simulation and the data on overall processing accuracy, it can be found that the processing accuracy of all experimental objects is above 96%, especially for power grid systems C and F, with a processing accuracy of 99%. This data is much higher than the traditional manual analysis process, ensuring the accuracy and reliability of power grid monitoring and risk assessment.

[0061] It can be seen that through the integration of the first station-line-user relationship model and the first dynamic monitoring, not only efficient grid risk management is achieved, but also the power company's response capability, resource allocation and fault handling efficiency are improved as a whole, effectively ensuring the stability and security of power supply. The effective implementation of this innovative solution ensures that potential risks can be identified in a timely manner in the operation of modern power grids, thereby reducing economic losses and user burdens. Therefore, the present invention is creative.

[0062] Example 3, reference Figure 4 , as an embodiment of the present invention, provides a benchmark risk dynamic management system, including a model building module, a dynamic monitoring module, and a risk analysis module.

[0063] The model building module is used to collect data on zero-power users in the power grid, and integrate the zero-power users with the number of distribution transformer users to build the first-station line-transformer-user relationship model; the dynamic monitoring module is used to establish dynamic monitoring, display changes in the power grid operation status, and through the risk identification function based on the first-station line-transformer-user relationship model, real-time identify and evaluate the risks in power grid operation; the risk analysis module is used to automatically identify key equipment in the power grid and the risk level of the power grid after a fault, and rollingly update the benchmark risk report.

[0064] If the function 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 this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0065] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0066] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0067] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0068] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A benchmark risk dynamic management method, characterized in that: include: Collect zero-power user data and establish a first-station line-change user relationship model; Establishing the first dynamic monitoring; Automatically identify key equipment in the power grid and the risk level of the power grid after failure based on real-time operation data, and update the baseline risk report on a rolling basis.

2. The benchmark risk dynamic management method according to claim 1, characterized in that: The collecting of zero-power user data includes integrating the zero-power user data with the distribution and transformation user data.

3. The benchmark risk dynamic management method according to claim 2, characterized in that: The first station line change user relationship model includes a linkage analysis of the risk relationship between equipment and users.

4. The benchmark risk dynamic management method according to claim 3, characterized in that: The first dynamic monitoring includes displaying changes in the operating status of the power grid.

5. The benchmark risk dynamic management method according to claim 4, characterized in that: The first dynamic monitoring also includes risk identification based on the first station line change user relationship model.

6. The benchmark risk dynamic management method according to claim 5, characterized in that: The automatic identification of key equipment in the power grid includes topology deduction based on N-1 and N-2 analysis methods to automatically identify key equipment in the power outage area; Comprehensive topological scanning and calculation are performed through breadth-first search and depth-first search algorithms.

7. The baseline risk dynamic management method according to claim 6, characterized in that: The rolling update baseline risk report includes setting up faulty equipment, superimposing normal operating modes for risk identification, calculating key equipment on the link, and based on the key equipment, conducting risk assessments from five dimensions: reduced load, depressurized plants, number of users affected, proportion of load loss, and proportion of number of users lost. Risk scores are calculated, and finally accident or event levels are listed to generate a baseline risk list.

8. A system using the benchmark risk dynamic management method according to any one of claims 1 to 7, characterized in that: Including model building module, dynamic monitoring module, and risk analysis module; The model building module is used to collect data on zero-power users in the power grid, and merge the zero-power users with the number of users of each distribution transformer to build a first station-line-transformer-user relationship model; The dynamic monitoring module is used to establish dynamic monitoring, display the changes in the operation status of the power grid, and identify and evaluate the risks in the operation of the power grid in real time through the risk identification function based on the first station line change user relationship model; The risk analysis module is used to automatically identify key equipment in the power grid and the risk level of the power grid after a failure, and to update the baseline risk report in a rolling manner.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the baseline risk dynamic management method described in any one of claims 1 to 7 are implemented.

10. 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 of the baseline risk dynamic management method described in any one of claims 1 to 7 are implemented.

Images