A high-stability power supply system and method for major events

Abstract

The present application provides a highly stable power supply system and method for major events, which relates to the field of digital twin technology, including: collecting power grid node data sets, and predicting power supply through virtual mapping of the power grid; collecting power consumption related data sets and inputting regional power consumption twin models to predict power consumption in the first period; generating multiple initial power supply plans based on the constraint of meeting the predicted power demand; performing multi-scenario power supply simulation on multiple initial power supply plans through the scheduling twin model, evaluating and determining the optimal power supply plan, and executing power grid scheduling in the first period. The present application can solve the technical problem in the prior art that the power system is difficult to ensure the power supply quality during major events due to the lack of flexibility of traditional power grids in dealing with sudden load changes, and realize the technical goal of intelligent scheduling and flexibility improvement of power grids, so as to achieve the technical effect of ensuring safe, reliable and uninterrupted power supply during major events.

Description

Technical Field

[0001] The present application relates to the field of digital twin technology, and in particular to a high-stability power supply protection system and method for major events. Background Art

[0002] With the acceleration of urbanization and rapid economic development, the demand for electricity is increasing, and traditional power grids are facing increasingly severe challenges. The current power system mainly relies on centralized power generation and traditional power supply methods. Although it can meet the power demand for a certain period of time, with the fluctuation of power load, the access of renewable energy, and extreme weather caused by climate change, this traditional model has gradually exposed its shortcomings. Traditional power grids lack flexibility in dealing with sudden load changes and power supply failures. For example, during large-scale events such as the Olympic Games, the sudden increase in power demand often makes it difficult for traditional power grids to quickly adjust the power supply plan to meet the demand, which may lead to insufficient power supply and voltage fluctuations.

[0003] To sum up, there are technical problems in the existing technology that the traditional power grid is not flexible enough in dealing with sudden load changes, resulting in the inability to quickly adjust the power supply plan to meet the power demand of major events, further affecting the stability and reliability of the power supply, making it difficult for the power system to ensure the power supply quality during major events, thereby causing a series of problems such as insufficient power supply and voltage fluctuations, interfering with the normal life and production activities of users, and also increasing the operating risks and maintenance costs of power companies. Summary of the invention

[0004] The purpose of this application is to provide a high-stability power supply protection system and method for major events, so as to solve the technical problems in the prior art that the traditional power grid is not flexible enough in dealing with sudden load changes, resulting in the inability to quickly adjust the power supply plan to meet the power demand of major events, further affecting the stability and reliability of the power supply, making it difficult for the power system to ensure the power supply quality during major events, thereby causing a series of problems such as insufficient power supply and voltage fluctuations, causing interference with the normal life and production activities of users, and also increasing the operating risks and maintenance costs of power companies.

[0005] In view of the above problems, the present application provides a high-stability power supply protection system and method for major events.

[0006] In the first aspect, the present application also provides a high-stability power supply protection system for major events, including: a power supply prediction unit, which is used to construct a virtual mapping of the power grid based on the simulation of the main power grid, distributed power grid and power supply relationship topology, collect power grid node data sets, perform power supply prediction through the virtual mapping of the power grid, and obtain a predicted power supply resource set for the first time period; a power consumption prediction unit, which is used to construct a regional power consumption twin model based on digital twin simulation, collect power consumption-related data sets and input them into the regional power consumption twin model to perform power consumption prediction for the first time period, and obtain a predicted power demand set; a demand judgment unit, which is used to judge whether the predicted power supply resource set meets the predicted power demand set based on the power supply relationship topology, and if so, generate multiple initial power supply plans based on the predicted power supply resource set with satisfying the predicted power demand as a constraint; a simulation evaluation unit, which is used to generate a scheduling twin model by integrating the virtual mapping of the power grid and the power consumption twin model, and perform multi-scenario power supply simulation on the multiple initial power supply plans through the scheduling twin model, determine the optimal power supply plan based on the simulation results, and execute the power grid scheduling for the first time period.

[0007] In the second aspect, the present application provides a high-stability power supply guarantee method for major events, which is implemented through a high-stability power supply guarantee system for major events, including: constructing a virtual mapping of the power grid through topological simulation of the main power grid, distributed power grid and power supply relationship, collecting power grid node data sets, performing power supply prediction through the virtual mapping of the power grid, and obtaining a predicted power supply resource set for the first time period; constructing a regional power consumption twin model based on digital twin simulation, collecting power consumption-related data sets and inputting the regional power consumption twin model to perform power consumption prediction for the first time period, and obtaining a predicted power demand set; based on the power supply relationship topology, judging whether the predicted power supply resource set meets the predicted power demand set, and if so, generating multiple initial power supply plans based on the predicted power supply resource set with satisfying the predicted power demand as a constraint; integrating the virtual mapping of the power grid and the power consumption twin model to generate a scheduling twin model, performing multi-scenario power supply simulation on the multiple initial power supply plans through the scheduling twin model, determining the optimal power supply plan based on the simulation results, and executing the power grid scheduling for the first time period.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] A power grid virtual map is constructed by simulating the main power grid, distributed power grid and power supply relationship topology, and a power grid node data set is collected. A power supply forecast is performed through the power grid virtual map to obtain a predicted power supply resource set for the first time period; a regional power consumption twin model is constructed based on digital twin simulation, and a power consumption related data set is collected and input into the regional power consumption twin model to perform power consumption forecast for the first time period to obtain a predicted power demand set; based on the power supply relationship topology, it is determined whether the predicted power supply resource set meets the predicted power demand set. If it does, multiple initial power supply plans are generated based on the predicted power supply resource set with the constraint of meeting the predicted power demand; a scheduling twin model is generated by integrating the power grid virtual map and the power consumption twin model, and a multi-scenario power supply simulation is performed on the multiple initial power supply plans through the scheduling twin model, and the optimal power supply plan is determined according to the simulation result evaluation, and the power grid scheduling for the first time period is executed to achieve the technical goal of intelligent scheduling and flexibility improvement of the power grid, so as to quickly adjust the power supply plan when dynamic load changes and emergencies occur, so as to ensure the stability and reliability of power supply during major events, thereby effectively reducing the occurrence of problems such as insufficient power supply and voltage fluctuations, and improving user satisfaction and the overall operation efficiency of the power system.

[0010] 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 according to the contents of the specification, and 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 specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 This is a structural schematic diagram of a high-stability power supply system for major events in this application.

[0013] Figure 2 This is a flow chart of a high-stability power supply method for major events in this application.

[0014] Explanation of the reference numerals: power supply prediction unit 11 , power consumption prediction unit 12 , demand judgment unit 13 , simulation evaluation unit 14 . DETAILED DESCRIPTION

[0015] The present application provides a high-stability power supply protection system and method for major events, thereby solving the problem in the prior art that the traditional power grid is not flexible enough in dealing with sudden load changes, resulting in the inability to quickly adjust the power supply plan to meet the power demand of major events, further affecting the stability and reliability of power supply, making it difficult for the power system to ensure the power supply quality during major events, thereby causing a series of problems such as insufficient power supply and voltage fluctuations, causing interference with the normal life and production activities of users, and also increasing the operating risks and maintenance costs of power companies. The application realizes the technical goal of intelligent scheduling and improved flexibility of the power grid, and achieves the technical effect of quickly adjusting the power supply plan when dynamic load changes and emergencies occur, so as to ensure the stability and reliability of power supply during major events, thereby effectively reducing the occurrence of problems such as insufficient power supply and voltage fluctuations, and improving user satisfaction and the overall operating efficiency of the power system.

[0016] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0017] For example, please refer to the attached Figure 1 , the present application provides a high-stability power supply system for major events, specifically including:

[0018] The power supply prediction unit 11 is used to construct a power grid virtual map by topological simulation of the main power grid, the distributed power grid and the power supply relationship, collect power grid node data sets, perform power supply prediction through the power grid virtual map, and obtain a predicted power supply resource set for the first time period.

[0019] Specifically, in the high-stability power supply system for major events, the main power grid refers to the main high-voltage transmission network, which is responsible for transmitting electricity from power plants to various user areas, including multiple substations and distribution networks. Distributed power grids refer to small power generation facilities built near users, which can directly provide electricity to local users, such as rooftop solar panels. The power supply relationship topology is the connection relationship between various nodes in the power grid (such as substations and users). Modeling and simulation are performed based on the main power grid, distributed power grid and power supply relationship topology to better understand and optimize the flow of power, and then collect power grid node data sets, such as recording the voltage, current and load conditions of each node. Furthermore, power supply prediction is performed using virtual mapping of the power grid, that is, based on historical data and real-time information, the power supply situation in a certain period of time in the future is estimated, and the predicted power supply resource set for the first period of time is obtained. For example, it is expected that the power supply capacity of a certain area may reach 200 megawatts in the next hour, thereby effectively supporting power dispatching and management.

[0020] The electricity consumption prediction unit 12 is used to build a regional electricity consumption twin model based on digital twin simulation, collect electricity consumption related data sets and input them into the regional electricity consumption twin model to perform electricity consumption prediction for the first period of time, and obtain a predicted electricity demand set.

[0021] Specifically, a regional power twin model is constructed based on digital twin simulation to simulate and analyze the power consumption in a specific area. Digital twin is a technology that corresponds to actual physical objects through digital technology, reflecting changes in the real world in real time. Next, the process of collecting power consumption related data sets and inputting them into the regional power twin model includes collecting relevant data, such as historical power consumption, weather conditions, event arrangements, etc., to ensure that the regional power twin model can perform accurate analysis. For example, if the power consumption during major events such as concerts increases by 20%. Then, the input data is used to predict the power consumption in the first period, predict the power demand in a certain time period in the future, and calculate that the region needs 350 kilowatts of electricity in the next hour through the regional power twin model. Finally, the obtained predicted power demand set provides an important basis for power grid management and dispatching, which helps to optimize the configuration of power resources and ensure the stability of power supply.

[0022] The demand judgment unit 13 is used to judge whether the predicted power supply resource set meets the predicted power demand set based on the power supply relationship topology, and if so, generate multiple initial power supply plans based on the predicted power supply resource set with satisfying the predicted power demand as a constraint.

[0023] Specifically, based on the power supply relationship topology, the analysis of each node and connection relationship in the power grid is carried out to obtain the relationship between power supply capacity and power demand, determine whether the predicted power supply resource set meets the predicted power demand set, and compare the power that the power grid can provide with the power demand of each event venue or major event area. For example, if the predicted power supply resource set shows that the power grid can provide 600 kilowatts of power in the next hour, and the predicted power demand set shows that the total demand of each event venue or event area is 500 kilowatts, it can be judged that the power supply of the power grid meets the demand. If this condition is met, multiple initial power supply plans will be generated based on the predicted power supply resource set with the constraint of meeting the predicted power demand, such as allocating 600 kilowatts of power between different event venues or event areas to ensure that the needs of all users can be met. The initial power supply plans that may be generated include allocating 300 kilowatts to specific stadiums, 200 kilowatts to exhibition centers, and 100 kilowatts to other activity areas, so as to effectively utilize power resources and ensure the rationality of power supply.

[0024] The simulation evaluation unit 14 is used to integrate the virtual mapping of the power grid and the power consumption twin model to generate a scheduling twin model, and perform multi-scenario power supply simulation on the multiple initial power supply plans through the scheduling twin model, determine the optimal power supply plan based on the simulation results, and execute the power grid scheduling in the first time period.

[0025] Specifically, the virtual mapping of the power grid and the power consumption twin model are integrated to generate a dispatch twin model, which digitally integrates the actual operation of the power grid with the user's power demand in order to better simulate and predict the relationship between power supply and demand. The virtual mapping of the power grid provides information on the connection and power flow between nodes in the power grid, while the power consumption twin model reflects the power consumption behavior and characteristics of different user areas. For example, the power consumption pattern in residential areas reaches its maximum during the evening peak period. By combining the generation of the dispatch twin model, real-time data support is provided for power grid dispatch.

[0026] Next, the scheduling twin model is used to perform multi-scenario power supply simulations on multiple initial power supply plans, and the effects of various power supply plans are tested under different loads, equipment conditions and weather conditions. For example, the power supply capacity of a power supply plan under normal weather conditions is 500 kilowatts, but it may be only 400 kilowatts under severe weather conditions. The optimal power supply plan is determined based on the simulation results, and the simulation data under different scenarios are analyzed to select the power supply plan with the best performance in all scenarios. Finally, executing the first period of grid scheduling means applying the determined optimal power supply plan to the actual grid operation to ensure that the user's electricity demand can be effectively met within a specific time period and to maintain the stability and security of the grid.

[0027] The highly stable power supply protection system for major events can achieve the technical goals of intelligent scheduling and flexibility improvement of the power grid, and quickly adjust the power supply plan when dynamic load changes and emergencies occur, so as to ensure the stability and reliability of power supply during major events, thereby effectively reducing the occurrence of problems such as power shortage and voltage fluctuations, and improving user satisfaction and the overall operating efficiency of the power system.

[0028] Furthermore, the present application also includes:

[0029] Collect a grid node data set, wherein the grid node data set includes voltage, current, load, equipment status and environmental factors; input the voltage, current, load, equipment status and environmental factors into the grid virtual mapping to perform power supply prediction for a first period of time, and output a first predicted power supply resource set; input the voltage, current, load, equipment status and environmental factors into a grid analyzer to perform power supply prediction for the first period of time, and output a second predicted power supply resource set, wherein the grid analyzer is constructed based on a long short-term memory network; configure credibility based on the first prediction accuracy and the second prediction accuracy, use the credibility to merge the first predicted power supply resource set and the second predicted power supply resource set, and output the predicted power supply resource set.

[0030] Specifically, collecting grid node data sets is a basic step in the management of high-stability power supply systems for major events. Grid node data sets include information such as voltage, current, load, equipment status, and environmental factors. Voltage refers to the voltage value of each node in the grid, current is the amount of current flowing through each node, load represents the power demand of each user in the grid, and equipment status represents the operation of the equipment, such as the status of the transformer is "normal operation", while environmental factors include temperature, humidity, etc. For example, the temperature is 30 degrees Celsius, which reflects the operation of the grid.

[0031] Next, the collected voltage, current, load, equipment status and environmental factors are input into the power grid virtual mapping system to make a power supply forecast for the first period, predict the power supply capacity of the power grid in the future, and output the first predicted power supply resource set, which will help power dispatchers make preparations in advance.

[0032] In addition, voltage, current, load, equipment status, and environmental factors are also input into the power grid analyzer for another power supply forecast, outputting a second set of predicted power supply resources. The power grid analyzer is built on a long short-term memory network, which can process time series data and learn historical power usage patterns to provide more accurate forecasts. For example, the long short-term memory network uses data from the past few days to predict power demand in the next hour, providing additional information for the power system.

[0033] Finally, the credibility is configured based on the historical prediction performance of each model. For example, if the accuracy of the first prediction is 85% and the accuracy of the second prediction is 90%, a higher weight can be given to the second prediction, thereby improving the reliability of the overall prediction. Then the credibility is configured based on the first prediction accuracy and the second prediction accuracy. By using the credibility, the first predicted power supply resource set and the second predicted power supply resource set are merged, and finally a comprehensive predicted power supply resource set is output.

[0034] By collecting multi-dimensional data of power grid nodes, using virtual mapping and power grid analyzers to predict power supply, and fusing the results based on the credibility of different models, the power supply prediction capability of the power system can be effectively improved to ensure the stability and security of power supply.

[0035] Furthermore, the present application also includes:

[0036] Based on the power supply relationship topology, the target area is divided into modules according to predetermined functions to determine multiple module areas; power consumption related data are collected for the multiple module areas respectively to obtain power consumption related data sets, wherein the power consumption related data at least includes venue type, event arrangement, event impact and environmental parameters; the power consumption related data sets are respectively input into the power consumption predictor and the regional power consumption twin model to perform power consumption forecasting for the first time period, and a first predicted power demand set and a second predicted power demand set are output, and the predicted power demand set is obtained by fusion.

[0037] Specifically, based on the power supply relationship topology, the target area is divided into modules according to predetermined functions, such as sports venue types, to ensure the rational allocation and efficient use of power resources.

[0038] Next, collect electricity-related data for multiple module areas to obtain electricity-related data sets. The electricity-related data sets contain multiple important information, including at least the type of venue (such as stadiums, convention centers), event arrangements (such as game schedules), event impact (such as the impact of the game on surrounding electricity consumption) and environmental parameters (such as temperature, humidity, etc.). For example, by predicting the flow of people during a large-scale sports event based on the event impact, the power demand of the stadium can be obtained to increase by 50% on the day of the game.

[0039] In addition, the acquired electricity consumption related data set is input into the electricity consumption predictor and the regional electricity consumption twin model to perform electricity consumption forecasting for the first period, thereby outputting the first predicted electricity demand set and the second predicted electricity demand set. By analyzing the historical electricity consumption data and current conditions, the electricity demand of each module in the next time period is predicted. For example, the forecast results show that the electricity demand of a module in the next hour is 200 kilowatts, while the other module is predicted to be 150 kilowatts. By analyzing the two forecast results, a more comprehensive forecast electricity demand set is obtained.

[0040] By dividing the area into modules based on the power supply relationship topology, collecting power consumption related data and using the prediction model to predict power demand, efficient management and allocation of power resources can be achieved, thereby ensuring that the power demand of different module areas is met within a specific time period.

[0041] Furthermore, the present application also includes:

[0042] If the predicted power supply resource set does not meet the predicted power demand set, a power priority analysis is performed based on the power-related data set to determine multiple real-time power priorities for multiple module areas and generate a power priority sequence; based on the power priority sequence and the power supply relationship topology, the power grid scheduling for the first time period is executed.

[0043] Specifically, if the predicted power supply resource set fails to meet the predicted power demand set, that is, when the power supply is insufficient, the power priority analysis will be conducted based on the power-related data set to evaluate the importance of the power demand of each module area, so as to determine which areas' power demand should be met first. For example, in an emergency, the power demand of a hospital may be evaluated as the highest priority, while the power demand of some non-essential commercial areas may be downgraded. The generated power priority sequence will help power grid managers make reasonable decisions in scheduling.

[0044] Next, based on the power priority sequence and power supply relationship topology, the grid dispatch for the first period is executed, and the corresponding power distribution is carried out according to the determined priority and the power supply capacity of the grid. For example, if a hospital is rated as the highest priority and its power demand is 500 kilowatts, while the demand of the commercial area is 300 kilowatts, the grid dispatch will give priority to guaranteeing the power supply of the hospital, while the commercial area may be subject to power restriction measures to ensure the effective use of power resources and the safety of users.

[0045] When it is predicted that power supply resources are insufficient to meet power demand, power priority analysis can be used to formulate priority power supply strategies for different module areas, and grid scheduling can be performed according to these priorities, thereby optimizing the allocation of power resources and ensuring power safety in key areas.

[0046] Furthermore, the present application also includes:

[0047] Taking the virtual mapping of the power grid and the electricity consumption twin model as similarity comparison constraints, a set of sample power supply scenarios is obtained based on power big data retrieval, wherein the sample power supply scenarios include load characteristics, equipment status, weather characteristics and emergencies; the sample power supply scenario set is subjected to scenario dimensionality reduction to determine a plurality of virtual power supply scenarios; based on the plurality of virtual power supply scenarios, the plurality of initial power supply schemes are respectively subjected to multi-scenario parallel simulation through the scheduling twin model to obtain a plurality of simulated power supply data sets; the plurality of simulated power supply data sets are respectively subjected to fitness evaluation through a power supply evaluation function, and the initial power supply scheme with the maximum fitness is selected as the optimal power supply scheme.

[0048] Specifically, with the virtual mapping of the power grid and the twin model of electricity consumption as similarity comparison constraints, when analyzing the relationship between power supply and demand, the virtual model of the actual power grid is compared with the simulation model of electricity demand, thereby establishing a basic framework. Based on the retrieval of power big data, a set of sample power supply scenarios is obtained, that is, big data technology is used to extract relevant information from historical and real-time data to form a database containing a variety of power supply situations. Sample power supply scenarios include load characteristics (such as peak and trough power consumption), equipment status (such as whether the equipment is operating normally), weather characteristics (such as temperature, humidity), and emergencies (such as power outages or equipment failures). For example, in the summer, the sample shows that the power demand under high load conditions has increased by 40%.

[0049] Next, the step of reducing the dimension of the sample power supply scenario set aims to simplify complex data. By compressing data of multiple dimensions into several important virtual power supply scenarios, key information can be extracted for subsequent analysis, which can effectively reflect the operation status of the power grid under different conditions. For example, three typical scenarios are extracted from multiple power supply scenarios, corresponding to high load, normal load and low load respectively.

[0050] Then, based on multiple virtual power supply scenarios, the scheduling twin model is used to perform multi-scenario parallel simulations on multiple initial power supply plans, simulating the operation of power supply plans in different scenarios, and obtaining multiple simulated power supply data sets to evaluate the performance of each plan in different situations. For example, the power supply capacity of the power supply plan in a high-load scenario is 500 kilowatts, while in a low-load scenario it is 700 kilowatts.

[0051] Finally, the fitness of multiple simulated power supply data sets is evaluated through the power supply evaluation function, and the initial power supply scheme with the maximum fitness is selected as the optimal power supply scheme. The fitness evaluation evaluates the performance of each scheme in meeting power demand and optimizing resource allocation, such as power supply stability and efficiency. If a scheme performs well in various scenarios, for example, the average power supply capacity under different load conditions exceeds expectations, it is selected as the optimal power supply scheme.

[0052] By combining the virtual mapping of the power grid with the electricity consumption twin model, big data is used to obtain sample power supply scenarios. After dimensionality reduction processing and simulation analysis, the optimal power supply plan can be evaluated and selected, thereby improving the operating efficiency and reliability of the power system.

[0053] Furthermore, the present application also includes:

[0054] A first sample power supply scenario is randomly selected from the sample power supply scenario set, wherein the first sample power supply scenario includes a first load characteristic, a first device state, a first weather characteristic and a first emergency event; a similarity traversal comparison is performed on the first load characteristic and other load characteristics in the sample power supply scenario set, and the number of characteristics whose similarity deviation is greater than a predetermined load similarity threshold is counted, which is set as a first difference; if the first difference is greater than the difference threshold, a difference analysis is performed on the first device state, the first weather characteristic and the first emergency event in turn to determine a second difference, a third difference and a fourth difference; if the second difference, the third difference and the fourth difference are all greater than the difference threshold, the first sample power supply scenario is added to the multiple virtual power supply scenarios.

[0055] Specifically, a sample power supply scenario is randomly selected from the sample power supply scenario set to obtain the first sample power supply scenario, and then a specific power supply situation is obtained from the overall sample for in-depth analysis. The first sample power supply scenario contains a variety of key features, including the first load feature (such as the power demand in a certain period of time is 600 kilowatts), the first equipment status (such as the normal operation of the transformer), the first weather feature (such as the temperature is 30 degrees Celsius) and the first emergency (such as equipment failure). Randomly selecting samples ensures that the analysis results are representative and random.

[0056] Next, a similar traversal comparison is performed on the first load feature and other load features in the sample power supply scenario set, the similarity between the load feature of the selected sample and the load features of other samples is evaluated, and the number of features with similar deviations greater than a predetermined load similarity threshold is counted, which is set as the first difference degree. For example, if it is found that the deviations of three load features in other samples from the first load feature exceed the set threshold (such as 10%), the first difference degree will be recorded as 3.

[0057] If the first difference is greater than the difference threshold, the first device state, the first weather characteristic, and the first emergency will be analyzed in turn to evaluate the similarity with other characteristics in the sample set and determine the second, third, and fourth differences. If the analysis finds that the differences of the device state, weather characteristic, or emergency exceed the predetermined threshold (such as 15%), the corresponding difference index will increase accordingly, reflecting the significant differences between the first device state, the first weather characteristic, and the first emergency in different samples.

[0058] Finally, if the second difference, the third difference, and the fourth difference are all greater than the difference threshold, the first sample power supply scenario is added to multiple virtual power supply scenarios to ensure that only samples that show obvious differences in multiple features are included in the virtual scenarios, which helps to build a more comprehensive and accurate power supply model.

[0059] By randomly selecting sample power supply scenarios and conducting detailed difference analysis on their load characteristics, equipment status, weather characteristics and emergencies, we can effectively screen out representative power supply scenarios, and then enrich the database of virtual power supply scenarios, thereby improving the simulation and prediction accuracy of the power system.

[0060] Furthermore, the present application also includes:

[0061] Perform iterative difference comparison until the sample power supply scenario set is traversed and the number of virtual power supply scenarios is counted; if the number of virtual power supply scenarios is greater than a predetermined index, enhance the similarity threshold and continue to perform scenario dimensionality reduction until the number of virtual power supply scenarios is less than or equal to the predetermined index.

[0062] Specifically, during the analysis process, an iterative difference comparison is performed to continuously compare each sample in the sample power supply scenario set to identify the differences between it and other samples. The characteristics of different power supply scenarios are understood through the iterative process, thus providing a basis for subsequent data processing. The number of virtual power supply scenarios is counted to evaluate the number of valid scenarios generated during the comparison process. For example, suppose that 15 valid virtual power supply scenarios are generated during the traversal process.

[0063] If the number of virtual power supply scenarios is greater than the predetermined index, it indicates that the number of scenarios currently generated exceeds the set reasonable range. For example, if the predetermined index is 10 virtual power supply scenarios, but 15 are actually generated, measures need to be taken to adjust them. At this time, the similarity threshold will be enhanced and the similarity standard will be tightened to improve the quality of the generated scenarios, thereby reducing the number of redundant virtual scenarios. Next, the process of scene dimensionality reduction is continued in order to simplify complex data and make the generated virtual power supply scenarios more accurate and efficient. Finally, until the number of virtual power supply scenarios is less than or equal to the predetermined index, it is ensured that the final generated scene set is controllable in quantity and can effectively support subsequent analysis and decision-making.

[0064] The generated scenario set is continuously optimized through iterative difference comparison and statistics of the number of virtual power supply scenarios. When the number exceeds the predetermined index, the number of scenarios is effectively controlled by enhancing the similarity threshold and scenario dimensionality reduction to ensure that the final virtual power supply scenario is both rich and meets the preset requirements, thereby improving the analysis ability and prediction accuracy of the power system.

[0065] Furthermore, the present application also includes:

[0066] The power supply evaluation function is constructed based on voltage stability coefficient, current stability coefficient, fault recovery time and energy utilization rate, wherein power supply adaptability is positively correlated with voltage stability coefficient, current stability coefficient and energy utilization rate, and negatively correlated with fault recovery time.

[0067] Specifically, the expression of the power supply evaluation function is: .in, To stabilize the power supply weight, is the energy utilization weight, is the voltage stability weight, is the current stabilization weight, is the fault repair weight, is the voltage stability coefficient of the jth solution, is the current stability coefficient of the jth solution, is the fault recovery time of the jth solution, is the energy utilization rate of the jth solution.

[0068] The power supply evaluation function comprehensively evaluates the performance of the power system to ensure that a stable and efficient power supply is provided while meeting the power demand. The voltage stability factor refers to the degree of voltage fluctuation under different load conditions. It is determined by measuring the amplitude of voltage change. Ideally, the voltage stability factor should be close to 1, indicating that the voltage is stable. For example, when the voltage fluctuates within the rated value range by no more than ±5%, the voltage stability factor can be considered stable. The current stability factor indicates the stability of the current under various operating conditions. It is obtained by monitoring the instantaneous changes of the current. A stable current coefficient helps to avoid equipment overload and damage. In addition, the fault recovery time refers to the time required for the power system to restore normal power supply after a power failure. A shorter fault recovery time means that the system is more resilient in dealing with emergencies. For example, if a substation can restore power supply within 10 minutes after a fault, the reliability of power supply is significantly improved. The energy utilization rate refers to the ratio between actual power consumption and power generation. The ideal energy utilization rate is as close to 100% as possible, indicating that power generation resources are effectively utilized.

[0069] The adaptability of power supply is positively correlated with the voltage stability coefficient, current stability coefficient and energy utilization rate. The higher the voltage stability coefficient, current stability coefficient and energy utilization rate, the higher the adaptability of power supply, and the better the overall performance of the high-stability power supply system for major events. On the contrary, the fault recovery time is negatively correlated with the adaptability of power supply. The longer the fault recovery time, the lower the adaptability, indicating that the high-stability power supply system for major events has insufficient response capability when faults occur.

[0070] By constructing a power supply evaluation function based on voltage stability coefficient, current stability coefficient, fault recovery time and energy utilization rate, the power supply adaptability of the power system is evaluated, ensuring stable and efficient operation during the power supply process and timely responding to possible faults, thereby improving the overall reliability of the power system.

[0071] In summary, the high-stability power supply system for major events provided by this application has the following technical effects:

[0072] A power grid virtual map is constructed by simulating the main power grid, distributed power grid and power supply relationship topology, and a power grid node data set is collected. A power supply forecast is performed through the power grid virtual map to obtain a predicted power supply resource set for the first time period; a regional power consumption twin model is constructed based on digital twin simulation, and a power consumption related data set is collected and input into the regional power consumption twin model to perform power consumption forecast for the first time period to obtain a predicted power demand set; based on the power supply relationship topology, it is determined whether the predicted power supply resource set meets the predicted power demand set. If it does, multiple initial power supply plans are generated based on the predicted power supply resource set with the constraint of meeting the predicted power demand; a scheduling twin model is generated by integrating the power grid virtual map and the power consumption twin model, and a multi-scenario power supply simulation is performed on the multiple initial power supply plans through the scheduling twin model, and the optimal power supply plan is determined according to the simulation result evaluation, and the power grid scheduling for the first time period is executed to achieve the technical goal of intelligent scheduling and flexibility improvement of the power grid, so as to quickly adjust the power supply plan when dynamic load changes and emergencies occur, so as to ensure the stability and reliability of power supply during major events, thereby effectively reducing the occurrence of problems such as insufficient power supply and voltage fluctuations, and improving user satisfaction and the overall operation efficiency of the power system.

[0073] Embodiment 2: Based on the high-stability power supply system for major events in the above embodiment, and the same inventive concept, this application also provides a high-stability power supply method for major events, please refer to the attached Figure 2 ,include:

[0074] A virtual mapping of the power grid is constructed by simulating the topology of the main power grid, distributed power grid and power supply relationship, and a data set of power grid nodes is collected. Power supply prediction is performed through the virtual mapping of the power grid to obtain a predicted power supply resource set for the first time period; a regional power consumption twin model is constructed based on digital twin simulation, and a power consumption-related data set is collected and input into the regional power consumption twin model to perform power consumption prediction for the first time period to obtain a predicted power demand set; based on the power supply relationship topology, it is determined whether the predicted power supply resource set meets the predicted power demand set, and if so, multiple initial power supply plans are generated based on the predicted power supply resource set with satisfying the predicted power demand as a constraint; the virtual mapping of the power grid and the power consumption twin model are integrated to generate a scheduling twin model, and multi-scenario power supply simulation is performed on the multiple initial power supply plans through the scheduling twin model, and the optimal power supply plan is determined based on the simulation results, and the power grid scheduling for the first time period is executed.

[0075] Furthermore, the high-stability power supply method for major events also includes:

[0076] Collect a grid node data set, wherein the grid node data set includes voltage, current, load, equipment status and environmental factors; input the voltage, current, load, equipment status and environmental factors into the grid virtual mapping to perform power supply prediction for a first period of time, and output a first predicted power supply resource set; input the voltage, current, load, equipment status and environmental factors into a grid analyzer to perform power supply prediction for the first period of time, and output a second predicted power supply resource set, wherein the grid analyzer is constructed based on a long short-term memory network; configure credibility based on the first prediction accuracy and the second prediction accuracy, use the credibility to merge the first predicted power supply resource set and the second predicted power supply resource set, and output the predicted power supply resource set.

[0077] Furthermore, the high-stability power supply method for major events also includes:

[0078] Based on the power supply relationship topology, the target area is divided into modules according to predetermined functions to determine multiple module areas; power consumption related data are collected for the multiple module areas respectively to obtain power consumption related data sets, wherein the power consumption related data at least includes venue type, event arrangement, event impact and environmental parameters; the power consumption related data sets are respectively input into the power consumption predictor and the regional power consumption twin model to perform power consumption forecasting for the first time period, and a first predicted power demand set and a second predicted power demand set are output, and the predicted power demand set is obtained by fusion.

[0079] Furthermore, the high-stability power supply method for major events also includes:

[0080] If the predicted power supply resource set does not meet the predicted power demand set, a power priority analysis is performed based on the power-related data set to determine multiple real-time power priorities for multiple module areas and generate a power priority sequence; based on the power priority sequence and the power supply relationship topology, the power grid scheduling for the first time period is executed.

[0081] Furthermore, the high-stability power supply method for major events also includes:

[0082] Taking the virtual mapping of the power grid and the electricity consumption twin model as similarity comparison constraints, a set of sample power supply scenarios is obtained based on power big data retrieval, wherein the sample power supply scenarios include load characteristics, equipment status, weather characteristics and emergencies; the sample power supply scenario set is subjected to scenario dimensionality reduction to determine a plurality of virtual power supply scenarios; based on the plurality of virtual power supply scenarios, the plurality of initial power supply schemes are respectively subjected to multi-scenario parallel simulation through the scheduling twin model to obtain a plurality of simulated power supply data sets; the plurality of simulated power supply data sets are respectively subjected to fitness evaluation through a power supply evaluation function, and the initial power supply scheme with the maximum fitness is selected as the optimal power supply scheme.

[0083] Furthermore, the high-stability power supply method for major events also includes:

[0084] A first sample power supply scenario is randomly selected from the sample power supply scenario set, wherein the first sample power supply scenario includes a first load characteristic, a first device state, a first weather characteristic and a first emergency event; a similarity traversal comparison is performed on the first load characteristic and other load characteristics in the sample power supply scenario set, and the number of characteristics whose similarity deviation is greater than a predetermined load similarity threshold is counted, which is set as a first difference; if the first difference is greater than the difference threshold, a difference analysis is performed on the first device state, the first weather characteristic and the first emergency event in turn to determine a second difference, a third difference and a fourth difference; if the second difference, the third difference and the fourth difference are all greater than the difference threshold, the first sample power supply scenario is added to the multiple virtual power supply scenarios.

[0085] Furthermore, the high-stability power supply method for major events also includes:

[0086] Perform iterative difference comparison until the sample power supply scenario set is traversed and the number of virtual power supply scenarios is counted; if the number of virtual power supply scenarios is greater than a predetermined index, enhance the similarity threshold and continue to perform scenario dimensionality reduction until the number of virtual power supply scenarios is less than or equal to the predetermined index.

[0087] Furthermore, the high-stability power supply method for major events also includes:

[0088] The power supply evaluation function is constructed based on voltage stability coefficient, current stability coefficient, fault recovery time and energy utilization rate, wherein power supply adaptability is positively correlated with voltage stability coefficient, current stability coefficient and energy utilization rate, and negatively correlated with fault recovery time.

[0089] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The high-stability power supply protection system for major events and the specific examples in the aforementioned embodiment one are also applicable to the high-stability power supply protection method for major events in this embodiment. Through the aforementioned detailed description of the high-stability power supply protection system for major events, those skilled in the art can clearly understand the high-stability power supply protection method for major events in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here.

[0090] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A high-stability power supply system for major events, characterized in that: include: A power supply prediction unit is used to construct a power grid virtual map by topological simulation of the main power grid, the distributed power grid and the power supply relationship, collect a data set of power grid nodes, perform power supply prediction through the power grid virtual map, and obtain a predicted power supply resource set for the first time period; The power consumption prediction unit is used to build a regional power consumption twin model based on digital twin simulation, collect power consumption related data sets and input them into the regional power consumption twin model to perform power consumption prediction for a first period of time, and obtain a predicted power demand set; A demand judgment unit, configured to judge whether the predicted power supply resource set meets the predicted power demand set based on the power supply relationship topology, and if so, generate multiple initial power supply schemes based on the predicted power supply resource set with satisfying the predicted power demand as a constraint; A simulation evaluation unit, configured to generate a scheduling twin model by integrating the power grid virtual mapping and the power consumption twin model, perform multi-scenario power supply simulation on the multiple initial power supply schemes respectively through the scheduling twin model, determine the optimal power supply scheme according to the simulation result evaluation, and execute the power grid scheduling in the first time period; The scheduling twin model is used to perform multi-scenario power supply simulations on the multiple initial power supply schemes respectively, and an optimal power supply scheme is determined based on the simulation results, including: Taking the virtual mapping of the power grid and the power consumption twin model as similarity comparison constraints, a sample power supply scenario set is obtained based on power big data retrieval, wherein the sample power supply scenario includes load characteristics, equipment status, weather characteristics and emergencies; Performing scenario dimensionality reduction on the sample power supply scenario set to determine multiple virtual power supply scenarios; Based on the multiple virtual power supply scenarios, the multiple initial power supply schemes are respectively simulated in parallel using the scheduling twin model to obtain multiple simulated power supply data sets; The fitness of the multiple simulated power supply data sets is evaluated respectively by using a power supply evaluation function, and an initial power supply scheme with the maximum fitness is selected as the optimal power supply scheme.

2. A high-stability power supply system for major events according to claim 1, characterized in that: Get the predicted power supply resource set, including: Collecting grid node data sets, wherein the grid node data sets include voltage, current, load, equipment status and environmental factors; Inputting the voltage, current, load, equipment status and environmental factors into the power grid virtual mapping to perform power supply prediction for a first period of time, and outputting a first predicted power supply resource set; Inputting the voltage, current, load, equipment status and environmental factors into a power grid analyzer to perform power supply prediction for a first period of time, and outputting a second predicted power supply resource set, wherein the power grid analyzer is constructed based on a long short-term memory network; The credibility is configured based on the first prediction accuracy and the second prediction accuracy, the first prediction power supply resource set and the second prediction power supply resource set are merged using the credibility, and the prediction power supply resource set is output.

3. A high-stability power supply system for major events according to claim 1, characterized in that: Get the predicted electricity demand set, including: Based on the power supply relationship topology, the target area is divided into modules according to predetermined functions to determine a plurality of module areas; Collecting electricity consumption related data for the multiple module areas respectively to obtain electricity consumption related data sets, wherein the electricity consumption related data at least includes the type of venue, event arrangement, event impact and environmental parameters; The electricity consumption related data set is respectively input into the electricity consumption predictor and the regional electricity consumption twin model to perform electricity consumption forecasting for the first time period, and a first predicted electricity demand set and a second predicted electricity demand set are output, and the predicted electricity demand set is obtained by fusion.

4. A high-stability power supply system for major events according to claim 3, characterized in that: If the predicted power supply resource set does not meet the predicted power demand set, a power priority analysis is performed according to the power association data set to determine multiple real-time power priorities of multiple module areas and generate a power priority sequence; Based on the electricity priority sequence and the power supply relationship topology, power grid scheduling for the first time period is performed.

5. The high-stability power supply system for major events according to claim 1 is characterized in that: The sample power supply scenario set is subjected to scenario dimensionality reduction to determine multiple virtual power supply scenarios, including: Randomly selecting a first sample power supply scenario from the sample power supply scenario set, wherein the first sample power supply scenario includes a first load characteristic, a first device state, a first weather characteristic, and a first emergency event; Performing a similarity traversal comparison on the first load feature and other load features in the sample power supply scenario set, and counting the number of features whose similarity deviation is greater than a predetermined load similarity threshold, setting the number of features as a first difference degree; If the first difference is greater than the difference threshold, performing difference analysis on the first device state, the first weather characteristic, and the first emergency event in sequence to determine a second difference, a third difference, and a fourth difference; If the second difference, the third difference, and the fourth difference are all greater than the difference threshold, the first sample power supply scenario is added to the multiple virtual power supply scenarios.

6. A high-stability power supply system for major events according to claim 5, characterized in that: Adding the first sample power supply scenario to the multiple virtual power supply scenarios, and then further comprising: Perform iterative difference comparison until the sample power supply scenario set is traversed and the number of virtual power supply scenarios is counted; If the number of virtual power supply scenarios is greater than a predetermined index, the similarity threshold is enhanced, and the scenario dimension reduction is continued until the number of virtual power supply scenarios is less than or equal to the predetermined index.

7. A high-stability power supply system for major events according to claim 1, characterized in that: The power supply evaluation function is constructed based on voltage stability coefficient, current stability coefficient, fault recovery time and energy utilization rate, wherein power supply adaptability is positively correlated with voltage stability coefficient, current stability coefficient and energy utilization rate, and negatively correlated with fault recovery time.

8. A high-stability power supply method for major events, characterized in that: The method for protecting power for major events with high stability is performed by a high-stability power protection system for major events according to any one of claims 1 to 7, and the method comprises: Constructing a virtual power grid mapping by topological simulation of the main power grid, the distributed power grid and the power supply relationship, collecting a data set of power grid nodes, performing power supply prediction through the virtual power grid mapping, and obtaining a predicted power supply resource set for the first time period; Building a regional electricity consumption twin model based on digital twin simulation, collecting electricity consumption related data sets and inputting them into the regional electricity consumption twin model to perform electricity consumption forecasting for the first period, and obtaining a forecast electricity demand set; Based on the power supply relationship topology, determine whether the predicted power supply resource set meets the predicted power demand set, and if so, generate multiple initial power supply plans based on the predicted power supply resource set with satisfying the predicted power demand as a constraint; The grid virtual mapping and the power consumption twin model are integrated to generate a scheduling twin model, and multi-scenario power supply simulations are performed on the multiple initial power supply schemes through the scheduling twin model. The optimal power supply scheme is determined according to the simulation results, and the grid scheduling of the first time period is executed; Furthermore, the high-stability power supply method for major events also includes: Taking the virtual mapping of the power grid and the electricity consumption twin model as similarity comparison constraints, a set of sample power supply scenarios is obtained based on power big data retrieval, wherein the sample power supply scenarios include load characteristics, equipment status, weather characteristics and emergencies; the sample power supply scenario set is subjected to scenario dimensionality reduction to determine a plurality of virtual power supply scenarios; based on the plurality of virtual power supply scenarios, the plurality of initial power supply schemes are respectively subjected to multi-scenario parallel simulation through the scheduling twin model to obtain a plurality of simulated power supply data sets; the plurality of simulated power supply data sets are respectively subjected to fitness evaluation through a power supply evaluation function, and the initial power supply scheme with the maximum fitness is selected as the optimal power supply scheme.

Images