Urban power distribution network toughness recovery management system in extreme weather

Abstract

The invention relates to the technical field of power distribution network recovery, in particular to an urban power distribution network toughness recovery management system under extreme weather, which comprises the steps of acquiring voltage, current, temperature, humidity and wind speed in real time, cleaning, formatting and standardizing data, identifying abnormal conditions influencing the stability of a power grid, evaluating the performance of the power grid under the extreme weather, and managing the toughness of the power distribution network under the extreme weather. An optimization suggestion is provided, various extreme weather scenes are simulated, feedback data are generated, comprehensive risk assessment is carried out, a coping strategy is generated, a fault point needing emergency processing is identified, recovery resources are dispatched, and a result is analyzed in real time to dynamically optimize an operation strategy of a power grid; according to the invention, by introducing the scene simulation and virtual training module, complex dynamic scene simulation is carried out, and coping strategies are verified and optimized. Feedback data generated by the system in simulation is used for further optimizing strategies in the toughness evaluation and decision support module, and adaptability and effectiveness of the strategies in actual extreme weather events are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of power distribution network restoration, and in particular to a management system for the resilience restoration of urban power distribution networks under extreme weather conditions. Background Art

[0002] As global climate change intensifies, the frequency and intensity of extreme weather events have increased significantly, posing a huge challenge to the stability and reliability of urban distribution networks. Under extreme weather conditions, such as typhoons, heavy rains, and snowstorms, natural disasters may cause large-scale power outages, affecting residents' lives and the normal operation of cities. Traditional power restoration methods often rely on manual inspections and physical repairs, which are inefficient and difficult to respond to large-scale power outages in a timely manner.

[0003] In recent years, with the development of smart grid technology, the automation and intelligence level of distribution networks have been improved. However, the existing smart grid system still has problems such as slow response speed, low recovery efficiency, and unreasonable resource allocation when dealing with emergencies under extreme weather conditions. Therefore, designing a resilience management system that can quickly and effectively restore urban distribution networks under extreme weather conditions has become an important research topic.

[0004] However, the inventors have discovered that this technical solution still has at least the following defects:

[0005] First, data processing and transmission delays: In existing technologies, data collection and processing often rely on centralized control systems for centralized processing, which results in a certain delay in the transmission of data from sensors to the central system. Especially in the face of emergencies such as extreme weather, the centralized processing model cannot respond to the ever-changing power grid status in real time, which may result in key decisions not being made in a timely manner, affecting the stability and security of the power grid.

[0006] Second, lack of localized intelligent response capabilities: In traditional power grid management systems, the adjustment of operation strategies and emergency response mainly rely on the instructions of the central control system, lacking localized intelligent decision-making and execution capabilities. This model that relies on the central system is prone to failure when communication is interrupted or the load is too heavy, and cannot fully utilize local resources for rapid response, resulting in insufficient response capabilities of the power grid in emergencies, affecting the efficiency of fault repair and recovery speed.

[0007] Third, the adaptability and optimization of response strategies are insufficient: In existing technologies, the response strategies of power grids are often based on static risk assessments and limited scenario simulations, lacking the ability to be verified and optimized in complex and dynamic real-world environments. These strategies may not be flexible enough in the face of changing extreme weather conditions, and cannot be adjusted in time to respond to new threats. In addition, the lack of effective feedback mechanisms and continuous optimization means makes it difficult for strategies to achieve the expected results in actual implementation, affecting the overall resilience and responsiveness of the power grid. Summary of the invention

[0008] Based on the above objectives, the present invention provides a resilience recovery management system for urban distribution networks under extreme weather conditions.

[0009] The urban distribution network resilience recovery management system under extreme weather conditions includes data collection and processing modules, resilience assessment modules, scenario simulation and virtual training modules, decision support modules, emergency response modules, and edge computing and real-time optimization modules:

[0010] The data collection and processing module includes multiple sensors installed at key nodes of the power distribution network to collect voltage, current, temperature, humidity and wind speed in real time, transmit the data to the central control system through a wireless network, clean, format and standardize the data, identify abnormal conditions that affect the stability of the power grid, and fuse the data from different sensors;

[0011] The resilience assessment module obtains processed data from the data collection and processing module, and combines historical fault data to assess the performance of the power grid under extreme weather conditions, including analysis of the failure risk, recovery capability, and potential weaknesses of the power grid, and establishes a power grid resilience model to predict the impact of future extreme weather events on the power grid and put forward optimization suggestions;

[0012] The scenario simulation and virtual training module uses the power grid resilience model and data provided by the resilience assessment module to simulate various extreme weather scenarios through virtual reality (VR) and augmented reality (AR) technology, and conducts virtual drills to verify and optimize response strategies, generate feedback data, and optimize resilience assessment and decision support strategies;

[0013] The decision support module conducts a comprehensive risk assessment based on the analysis results of the resilience assessment module and the feedback data provided by the scenario simulation and virtual training modules, and generates response strategies, including load transfer, load reduction, and rapid fault repair, and pushes the optimized strategies to the emergency response module for execution;

[0014] The emergency response module identifies the fault points that need emergency treatment based on the strategies provided by the decision support module, dispatches repair resources, and communicates with the on-site repair team in real time;

[0015] The edge computing and real-time optimization module deploys edge computing units at key nodes of the power grid to process and analyze local data in real time. The edge computing units work in coordination with the central control system to dynamically optimize the operation strategy of the power grid through real-time analysis results.

[0016] Optionally, the data collection and processing module includes:

[0017] Sensor data collection: Multiple sensors are installed at key nodes of the distribution network to collect voltage, current, temperature, humidity and wind speed in real time;

[0018] Data transmission: The data collected by the above sensors in real time are transmitted to the central control system through a wireless network;

[0019] Data preprocessing: The central control system preprocesses the received data, including data cleaning, formatting and standardization operations;

[0020] Abnormal situation identification: Real-time analysis of pre-processed data to identify abnormal situations that affect grid stability, including equipment overheating and line overload;

[0021] Data fusion: Data from different sensors are fused and processed, and multi-source data are integrated into a single data set through a weighted average algorithm.

[0022] Optionally, the resilience assessment module includes:

[0023] Data acquisition: Receive processed real-time data from the data collection and processing module, including voltage, current, temperature, humidity and wind speed, and obtain historical fault data;

[0024] Failure risk assessment: Analyze the received real-time data and historical fault data to assess the failure risk of the power grid under current and predicted extreme weather conditions, and use the probabilistic risk analysis (PRA) method to calculate the probability of power grid failure P f , by integrating the risks of various fault events, the overall failure risk of the power grid under extreme weather conditions is obtained;

[0025] Restoration Capacity Assessment: Using the Grid Restoration Time T r and recovery cost C r The recovery time can be determined by the average recovery time of similar events in historical data, and the recovery cost is calculated based on the degree of equipment damage and the repair resource requirements;

[0026] Weakness analysis: Based on the failure risk and recovery capacity data, potential weak points in the power grid are identified. Cluster analysis and sensitivity analysis are used to identify nodes or devices that are prone to failure in extreme weather. Failure events with similar characteristics in historical failure data are grouped together to determine weak points.

[0027] Resilience model establishment: Based on the above data and analysis results, a Bayesian network is used to establish a power grid resilience model. The model nodes represent the key components or nodes of the power grid, and the edges represent the dependencies between components and the fault propagation paths. The model predicts the overall performance of the power grid under different extreme weather conditions by calculating the conditional probability of each node;

[0028] Optimization suggestion generation: Based on the output of the resilience model, suggestions are put forward to optimize the design and operation of the power grid, including equipment reinforcement, backup power configuration and optimization of emergency plans. The optimization suggestions are refined through sensitivity analysis.

[0029] Optionally, the scenario simulation and virtual training module includes:

[0030] Data and model acquisition: Obtain the grid resilience model and related data from the resilience assessment module, including the results of failure risk, recovery capability and weak point analysis;

[0031] Scenario setting: Different simulation scenarios are set according to the type of extreme weather (such as typhoons, heavy rains, ice and snow, etc.); each scenario setting includes weather parameters (such as wind speed, precipitation, temperature changes, etc.) and the initial conditions of the power grid (such as load conditions, equipment status, etc.);

[0032] Virtual reality (VR) and augmented reality (AR) environment construction: Use virtual reality and augmented reality technologies to create a virtual environment similar to the actual power grid, and input the set scenario parameters into the simulation environment. The system dynamically adjusts the performance of the power grid in the simulation based on the model and data provided by the resilience assessment module;

[0033] Virtual drills: Run simulation scenarios in a virtual environment, verify the effectiveness of existing response strategies by real-time monitoring of the simulated power grid response, analyze the performance of key nodes, including the response of weak points, and record the operation data of the power grid in the simulation scenario;

[0034] Feedback data generation: Based on the results of the virtual drill, feedback data is generated. The feedback data includes the performance of the power grid in the simulated scenario, including the time of fault occurrence, fault point distribution, and recovery time;

[0035] Optimization strategy generation: Utilize the generated feedback data to optimize the response strategies in the resilience assessment module and decision support module. By comparing the strategy effects before and after the simulation, adjust and optimize the strategies for grid operation and recovery.

[0036] Optionally, the virtual reality and augmented reality environment construction includes:

[0037] Virtual environment construction: Based on the grid resilience model and related data provided by the resilience assessment module, a virtual environment similar to the actual grid structure, equipment layout and operating status is constructed on the virtual reality (VR) and augmented reality (AR) platforms to simulate the physical characteristics and operating dynamics of the actual grid.

[0038] Scenario parameter input: input the preset extreme weather scenario parameters into the virtual environment. The scenario parameters include the type, intensity, duration of the extreme weather and the initial operation status of the power grid. After input, the virtual environment simulates the operation status of the power grid under specific conditions.

[0039] Dynamic Adjustment: During the simulation, the system dynamically adjusts the performance of the virtual grid based on real-time data and model analysis from the resilience assessment module, including changes in grid load, the occurrence and propagation of equipment failures, and the recovery process.

[0040] Optionally, the virtual drill includes:

[0041] Simulation scenario operation steps: Run the set extreme weather simulation scenario in the virtual environment constructed by virtual reality (VR) and augmented reality (AR);

[0042] Real-time monitoring step: During the simulation scenario operation, the response of each key node in the virtual power grid is monitored in real time, including voltage fluctuations, load changes and equipment failures. The system records the operation status of the power grid through real-time data streams and monitoring interfaces;

[0043] Response strategy verification step: During the simulation run, verify the effectiveness of the currently applied response strategy, and evaluate the execution effect of the strategy under different conditions by monitoring the performance of each key node, including the impact on grid stability and resilience;

[0044] Key node analysis step: Detailed analysis of the key nodes of the power grid in the simulation, focusing on the response of the weak points, including analyzing the fault occurrence time, impact range and recovery time of the weak points in the simulation scenario, and identifying the strategies or nodes that need to be improved;

[0045] Operation data recording steps: During the virtual drill, all operation data of the power grid under the simulated scenario are recorded in detail, including: fault occurrence time, fault point location, load transfer situation, recovery time and strategy execution effect.

[0046] Optionally, the decision support module includes:

[0047] Data integration and analysis: Obtain analysis results from the resilience assessment module, including assessment data on grid failure risk, recovery capabilities, and potential weaknesses; obtain and integrate feedback data from the scenario simulation and virtual training modules, including fault points and recovery time found in the simulation;

[0048] Risk assessment: Based on the integrated data, a comprehensive risk assessment is conducted, which includes classifying the risk levels of key nodes and components of the power grid, identifying high-risk areas that may cause serious impacts, and determining the overall risk level of the power grid through quantitative analysis;

[0049] Strategy generation: Based on the risk assessment results, generate response strategies for different scenarios, including:

[0050] Load transfer strategies: Identify feasible load transfer paths to relieve pressure on high-risk areas;

[0051] Load reduction strategy: In extreme cases, the stability of the core area of ​​the power grid is protected by appropriately reducing non-critical loads;

[0052] Fault fast repair strategy: Determine the optimal fault repair path and resource allocation plan to minimize the overall impact of the fault on the power grid;

[0053] Strategy optimization: Utilize the feedback data provided by the scenario simulation and virtual training modules to optimize the initially generated response strategies. By comparing the execution effects of the strategies under different simulation scenarios, adjust and improve the strategy parameters and execution plans.

[0054] Strategy push and execution: Push the optimized response strategy to the emergency response module. The push includes sending specific operation instructions to the on-site repair team and real-time monitoring and adjustment through the central control system.

[0055] Optionally, the emergency response module includes:

[0056] Fault point identification: Receive the optimization strategy provided by the decision support module, automatically identify the fault points in the power grid that need to be urgently handled based on the analysis results and priorities in the strategy, determine the key fault areas based on real-time data monitoring and strategy guidance, and use them as repair targets;

[0057] Repair resource scheduling: After the fault point is identified, the system automatically dispatches appropriate repair resources, including maintenance personnel, equipment, tools and spare parts. According to the severity and location of the fault, the system optimizes resource allocation;

[0058] Real-time communication and coordination steps: The system establishes a real-time communication link with the on-site repair team through the wireless communication network, transmits detailed information of the fault point, repair strategy and required resource list to the on-site team, and continuously monitors the repair progress. The system can also dynamically adjust the repair strategy based on on-site feedback;

[0059] Repair work monitoring steps: During the repair process, the emergency response module monitors the progress of the repair work in real time, collects on-site repair data, and synchronizes data with the decision support module. The system adjusts the strategy in a timely manner according to the progress of the repair to deal with unexpected situations;

[0060] Repair completion confirmation step: After the fault repair is completed, the system conducts a final inspection of the fault point to confirm whether the repair meets the expected results, and feeds back the repair completion status information to the central control system, recording the detailed data of the repair work.

[0061] Optionally, the edge computing and real-time optimization module includes:

[0062] Edge computing unit deployment: Edge computing units are deployed at key nodes of the power grid. The computing units have independent data processing and computing capabilities, and receive and process data from sensors in real time locally, including voltage, current, and temperature.

[0063] Local data processing: The edge computing unit processes the collected local data in real time, including data cleaning, anomaly detection, and preliminary analysis;

[0064] Real-time analysis and optimization: The edge computing unit analyzes the processed data in real time, evaluates the current grid operation status, and dynamically optimizes local operation strategies based on real-time data, including adjusting load distribution, optimizing power flow paths, and starting local backup power sources when necessary;

[0065] Collaborate with the central control system: The edge computing unit maintains real-time communication with the central control system, and synchronizes data and analysis results in both directions. The central control system pushes macro-level decisions and strategies to the edge computing unit, and the edge computing unit feeds back local real-time analysis results and execution status.

[0066] Dynamic adjustment and execution: Based on the central control system's strategy and real-time analysis results, the edge computing unit dynamically adjusts the operation strategy locally, including adjusting voltage levels and switching power paths, to cope with emergencies caused by extreme weather;

[0067] Recovery and monitoring: Under extreme weather conditions, the edge computing unit continuously monitors the status of the local power grid, dynamically adjusts and optimizes the power grid recovery strategy, and the execution status and effect data of all recovery operations will be synchronously transmitted to the central control system.

[0068] Optionally, the dynamic adjustment and execution includes:

[0069] Real-time data monitoring and analysis: The edge computing unit continuously monitors the real-time data of key nodes, including voltage, current, and load changes, and compares and analyzes the strategy data synchronously transmitted by the central control system;

[0070] Dynamic adjustment of voltage level: When the calculated voltage difference ΔV exceeds the predetermined threshold, the edge computing unit immediately performs the voltage adjustment operation. The adjustment strategy can be dynamically adjusted according to the real-time load demand and equipment status;

[0071] Power path switching: Based on real-time analysis results and the policy guidance of the central control system, when a power path is identified to have a fault or overload risk, the edge computing unit quickly performs the power path switching operation. During the switching process, the shortest path algorithm is used to calculate the alternative path and select the path with the least loss for power switching to minimize the loss of the power grid and maintain the stability of power supply.

[0072] Quick response and execution: In emergencies caused by extreme weather, the edge computing unit immediately performs the above-mentioned voltage adjustment and power path switching operations. The edge computing unit can respond quickly and effectively mitigate the deterioration of the power grid. When executing adjustments, the system continuously monitors the adjustment effects and optimizes the operation strategy based on feedback data.

[0073] Beneficial effects of the present invention:

[0074] The present invention realizes real-time data collection, processing and analysis by deploying edge computing units at key nodes of the power grid, significantly reducing the delay in data transmission to the central control system. This localized processing method enables the system to quickly adjust operating strategies in extreme weather, respond immediately to emergencies, ensure that key decisions can be made in a timely manner, and effectively improve the stability and security of the power grid.

[0075] The present invention endows the key nodes of the power grid with localized intelligent response capabilities, and the edge computing unit can dynamically optimize the operation strategy according to real-time data, such as adjusting the voltage level and switching the power supply path. With the coordinated work of the central control system and the edge computing unit, the system can quickly identify and repair faults, improve the efficiency and accuracy of emergency response, and can still independently complete the response and recovery operations, especially in the case of communication interruption or system overload.

[0076] The present invention introduces scenario simulation and virtual training modules, uses virtual reality (VR) and augmented reality (AR) technologies to simulate complex dynamic scenarios, verify and optimize response strategies. The feedback data generated by the system in the simulation is used to optimize the strategies in the resilience assessment and decision support modules, ensuring the adaptability and effectiveness of the strategies in actual extreme weather events, and significantly improving the overall resilience and rapid recovery capabilities of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the technical solutions in the present invention 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 for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0078] Figure 1 This is a schematic diagram of a management system for resilience recovery of a city distribution network under extreme weather conditions according to an embodiment of the present invention;

[0079] Figure 2 Schematic diagram of a scenario simulation and virtual training module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0080] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0081] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0082] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0083] like Figure 1-Figure 2 As shown in the figure, the urban distribution network resilience recovery management system under extreme weather conditions includes data collection and processing module, resilience assessment module, scenario simulation and virtual training module, decision support module, emergency response module, and edge computing and real-time optimization module:

[0084] The data collection and processing module includes multiple sensors installed at key nodes of the distribution network to collect voltage, current, temperature, humidity and wind speed in real time, transmit the data to the central control system through a wireless network, clean, format and standardize the data, identify abnormal conditions that affect the stability of the power grid, and fuse the data from different sensors to ensure the accuracy and reliability of the data;

[0085] The resilience assessment module obtains processed data from the data collection and processing module, and combines it with historical fault data to evaluate the performance of the power grid under extreme weather conditions, including analysis of the failure risk, recovery capability, and potential weaknesses of the power grid. It also establishes a power grid resilience model, predicts the impact of future extreme weather events on the power grid, and puts forward optimization suggestions.

[0086] The scenario simulation and virtual training module uses the grid resilience model and data provided by the resilience assessment module to simulate various extreme weather scenarios through virtual reality (VR) and augmented reality (AR) technology, conduct virtual drills, verify and optimize response strategies, generate feedback data, and optimize resilience assessment and decision support strategies.

[0087] The decision support module conducts a comprehensive risk assessment based on the analysis results of the resilience assessment module and the feedback data provided by the scenario simulation and virtual training modules, and generates response strategies, including load transfer, load reduction, and rapid fault repair, and pushes the optimized strategies to the emergency response module for execution;

[0088] The emergency response module identifies the fault points that need to be urgently handled based on the strategies provided by the decision support module, dispatches repair resources, and communicates with the on-site repair team in real time to ensure the efficient execution of the repair work;

[0089] The edge computing and real-time optimization module deploys edge computing units at key nodes of the power grid to process and analyze local data in real time, reduce data transmission delays and improve response speed. The edge computing units work together with the central control system to dynamically optimize the operation strategy of the power grid through real-time analysis results, ensuring rapid and effective restoration of power supply under extreme weather conditions.

[0090] The data collection and processing modules include:

[0091] Sensor data collection: Multiple sensors are installed at key nodes of the distribution network to collect voltage, current, temperature, humidity and wind speed in real time;

[0092] Data transmission: The data collected by the above sensors in real time are transmitted to the central control system through the wireless network to ensure the timeliness and stability of data transmission;

[0093] Data preprocessing: The central control system preprocesses the received data, including data cleaning, formatting and standardization operations to eliminate noise, erroneous data and inconsistent formats;

[0094] Abnormal situation identification: Real-time analysis of pre-processed data to identify abnormal situations that affect grid stability, including equipment overheating and line overload;

[0095] Data fusion: Data from different sensors are fused and processed. Multi-source data is integrated into a single data set through a weighted average algorithm to ensure the accuracy and reliability of the final data. The weighted average algorithm includes:

[0096] Let x 1 ,x 2 ,…,x n is the real-time data from n different sensors, w 1 ,w 2 ,…,w n are the weights of these sensors, and the fused single dataset X is expressed as:

[0097]

[0098] Weight w i The determination is based on the sensor accuracy p i , expressed as:

[0099]

[0100] The sensor with higher weight contributes more to the fusion result, and the sensor with high accuracy and good stability is given a larger weight, thereby reducing the uncertainty caused by the error of a single sensor and finally outputting a fused data set.

[0101] By collecting and transmitting key data in real time, combined with data preprocessing and abnormal situation identification, the accuracy and reliability of the data are ensured. Multi-source data is fused through a weighted average algorithm, making full use of the data advantages of high-precision sensors, reducing the impact of single sensor errors, and ultimately outputting a high-quality fused data set. This method improves the accuracy and stability of power grid monitoring, helps to promptly discover and respond to potential problems, and enhances the overall resilience and responsiveness of the system.

[0102] The resilience assessment modules include:

[0103] Data acquisition: Receive processed real-time data from the data collection and processing module, including voltage, current, temperature, humidity and wind speed, and obtain historical fault data to ensure that the data used for evaluation is comprehensive and accurate;

[0104] Failure risk assessment: Analyze the received real-time data and historical fault data to assess the failure risk of the power grid under current and predicted extreme weather conditions, and use the probabilistic risk analysis (PRA) method to calculate the probability of power grid failure P f , expressed as:

[0105]

[0106] Among them, P i represents the probability of occurrence of the ith failure event, C i Indicates the impact of the fault event on the entire power grid. By integrating the risks of various fault events, the overall failure risk of the power grid under extreme weather conditions is obtained.

[0107] Restoration Capacity Assessment: Using the Grid Restoration Time T r and recovery cost C r For evaluation, the recovery time can be determined by the average recovery time of similar events in historical data, expressed as:

[0108]

[0109] Among them, T j is the recovery time of the jth historical event, m is the number of historical events, and the recovery cost is calculated based on the degree of equipment damage and the demand for repair resources.

[0110] Weakness analysis: Based on the failure risk and recovery capacity data, potential weak points in the power grid are identified. Cluster analysis and sensitivity analysis are used to identify nodes or devices that are prone to failure in extreme weather. Failure events with similar characteristics in historical failure data are grouped together to determine weak points.

[0111] Resilience model establishment: Based on the above data and analysis results, a Bayesian network is used to establish a power grid resilience model. The model nodes represent the key components or nodes of the power grid, and the edges represent the dependencies between components and the fault propagation paths. The model predicts the overall performance of the power grid under different extreme weather conditions by calculating the conditional probability of each node;

[0112] Optimization suggestion generation: Based on the output of the resilience model, suggestions are put forward to optimize the design and operation of the power grid, including equipment reinforcement, backup power configuration and optimization of emergency plans. The optimization suggestions are refined through sensitivity analysis to ensure their operability and effectiveness in actual applications.

[0113] The scenario simulation and virtual training modules include:

[0114] Data and model acquisition: Obtain the grid resilience model and related data from the resilience assessment module, including the results of failure risk, recovery capability and weak point analysis, to ensure the integrity of the model and data so that the actual status of the grid can be accurately reflected in subsequent simulations;

[0115] Scenario setting: Different simulation scenarios are set according to the type of extreme weather (such as typhoons, heavy rains, ice and snow, etc.); each scenario setting includes weather parameters (such as wind speed, precipitation, temperature changes, etc.) and the initial conditions of the power grid (such as load conditions, equipment status, etc.);

[0116] Virtual reality (VR) and augmented reality (AR) environment construction: Use virtual reality and augmented reality technologies to create a virtual environment similar to the actual power grid, and input the set scenario parameters into the simulation environment. The system dynamically adjusts the performance of the simulated power grid based on the model and data provided by the resilience assessment module to make it consistent with the actual situation;

[0117] Virtual drills: Run simulation scenarios in a virtual environment, verify the effectiveness of existing response strategies by real-time monitoring of the simulated power grid response, analyze the performance of key nodes, including the response of weak points, and record the operation data of the power grid in the simulation scenario;

[0118] Feedback data generation: Based on the results of the virtual drill, feedback data is generated. The feedback data includes the performance of the power grid in the simulated scenario, including the time of fault occurrence, fault point distribution, and recovery time;

[0119] Optimization strategy generation: Utilize the generated feedback data to optimize the response strategies in the resilience assessment module and decision support module. By comparing the strategy effects before and after the simulation, adjust and optimize the grid operation and recovery strategies to improve the grid’s ability to respond to actual extreme weather events.

[0120] Through comprehensive data and model acquisition, scenario setting, virtual reality / augmented reality environment construction, virtual drills and feedback optimization, the performance of the power grid under extreme weather conditions is fully simulated. Through real-time monitoring and dynamic adjustment, the response strategy is verified and optimized to improve the resilience and responsiveness of the power grid under actual conditions. The generated feedback data is used to continuously improve the strategy to ensure more accurate and effective response to emergencies in real events and improve the overall safety and stability of the power grid.

[0121] The construction of virtual reality and augmented reality environments includes:

[0122] Virtual environment construction: Based on the grid resilience model and related data provided by the resilience assessment module, a virtual environment similar to the actual grid structure, equipment layout and operating status is constructed on the virtual reality (VR) and augmented reality (AR) platforms to simulate the physical characteristics and operating dynamics of the actual grid.

[0123] Scenario parameter input: input the preset extreme weather scenario parameters into the virtual environment. The scenario parameters include the type, intensity, duration of the extreme weather and the initial operation status of the power grid. After input, the virtual environment simulates the operation status of the power grid under specific conditions.

[0124] Dynamic adjustment: During the simulation, the system dynamically adjusts the performance of the virtual grid based on real-time data and model analysis from the resilience assessment module. The adjustments include changes in grid load, the occurrence and propagation of equipment failures, and the recovery process to ensure that the grid performance in the virtual environment is consistent with possible actual conditions.

[0125] The virtual walkthrough includes:

[0126] Simulation scenario operation steps: Run the set extreme weather simulation scenario in the virtual environment constructed by virtual reality (VR) and augmented reality (AR) to ensure that all weather parameters, power grid status and initial conditions in the simulation scenario accurately reflect the real possible situation;

[0127] Real-time monitoring step: During the simulation scenario operation, the response of each key node in the virtual power grid is monitored in real time, including voltage fluctuations, load changes and equipment failures. The system records the operation status of the power grid through real-time data streams and monitoring interfaces to ensure that abnormal situations can be discovered in a timely manner;

[0128] Response strategy verification step: During the simulation run, verify the effectiveness of the currently applied response strategy, and evaluate the execution effect of the strategy under different conditions by monitoring the performance of each key node, including the impact on grid stability and resilience;

[0129] Key node analysis step: Detailed analysis of the key nodes of the power grid in the simulation, focusing on the response of the weak points, including analyzing the fault occurrence time, impact range and recovery time of the weak points in the simulation scenario, and identifying the strategies or nodes that need to be improved;

[0130] Operation data recording steps: During the virtual drill, all operation data of the power grid under the simulated scenario are recorded in detail, including: fault occurrence time, fault point location, load transfer situation, recovery time and strategy execution effect, to ensure that all data is completely saved for subsequent analysis and optimization.

[0131] The decision support modules include:

[0132] Data integration and analysis: Obtain analysis results from the resilience assessment module, including assessment data on grid failure risk, recovery capabilities, and potential weaknesses; obtain and integrate feedback data from the scenario simulation and virtual training modules, including fault points and recovery time found in the simulation, to fully understand the potential risks and performance of the grid under extreme weather conditions;

[0133] Risk assessment: Based on the integrated data, a comprehensive risk assessment is conducted, which includes classifying the risk levels of key nodes and components of the power grid, identifying high-risk areas that may cause serious impacts, and determining the overall risk level of the power grid through quantitative analysis;

[0134] Strategy generation: Based on the risk assessment results, generate response strategies for different scenarios, including:

[0135] Load transfer strategies: Identify feasible load transfer paths to relieve pressure on high-risk areas;

[0136] Load reduction strategy: In extreme cases, the stability of the core area of ​​the power grid is protected by appropriately reducing non-critical loads;

[0137] Fault fast repair strategy: Determine the optimal fault repair path and resource allocation plan to minimize the overall impact of the fault on the power grid;

[0138] Strategy optimization: Utilize the feedback data provided by the scenario simulation and virtual training modules to optimize the initially generated response strategies. By comparing the execution effects of the strategies in different simulation scenarios, adjust and improve the parameters and execution plans of the strategies to ensure the best performance in actual applications.

[0139] Strategy push and execution: Push the optimized response strategies to the emergency response module to ensure that these strategies can be quickly executed. Push includes sending specific operation instructions to the on-site repair team and real-time monitoring and adjustment through the central control system to ensure the effective implementation of the strategy.

[0140] The emergency response module includes:

[0141] Fault point identification: Receive the optimization strategy provided by the decision support module, automatically identify the fault points in the power grid that need to be urgently handled based on the analysis results and priorities in the strategy, determine the key fault areas based on real-time data monitoring and strategy guidance, and use them as repair targets;

[0142] Repair resource scheduling: After the fault point is identified, the system automatically dispatches appropriate repair resources, including maintenance personnel, equipment, tools and spare parts. According to the severity and location of the fault, the system optimizes resource allocation to ensure that the necessary resources are deployed to the fault site in the shortest time;

[0143] Real-time communication and coordination steps: The system establishes a real-time communication link with the on-site repair team through the wireless communication network, transmits detailed information of the fault point, repair strategy and required resource list to the on-site team, and continuously monitors the repair progress. The system can also dynamically adjust the repair strategy based on on-site feedback to ensure smooth repair work;

[0144] Restoration work monitoring steps: During the restoration process, the emergency response module monitors the progress of the restoration work in real time, collects on-site restoration data, and synchronizes data with the decision support module. The system adjusts strategies in a timely manner according to the restoration progress to deal with unexpected situations and ensure efficient execution of the restoration work;

[0145] Repair completion confirmation step: After the fault repair is completed, the system conducts a final inspection of the fault point to confirm whether the repair meets the expected results, and feeds back the repair completion status information to the central control system, recording detailed data of the repair work for subsequent analysis and optimization of the emergency response capabilities of the power grid.

[0146] The system ensures rapid recovery of the power grid in extreme weather conditions by automatically identifying fault points, optimizing repair resource scheduling, real-time communication and coordination, and full monitoring and confirmation of repair work. The system automatically handles faults, improves response speed, reduces human errors, and responds to emergencies by adjusting strategies in real time. After the repair is completed, the system records and analyzes detailed data to provide valuable experience for future emergency responses, thereby enhancing the overall stability and risk resistance of the power grid.

[0147] Edge computing and real-time optimization modules include:

[0148] Edge computing unit deployment: Edge computing units are deployed at key nodes of the power grid. The computing units have independent data processing and computing capabilities, and receive and process data from sensors in real time locally, including voltage, current, and temperature.

[0149] Local data processing: The edge computing unit processes the collected local data in real time, including data cleaning, anomaly detection, and preliminary analysis. By completing these processes locally, the delay in data transmission to the central control system is reduced, ensuring that key decisions can be made in a timely manner.

[0150] Real-time analysis and optimization: The edge computing unit analyzes the processed data in real time, evaluates the current grid operation status, and dynamically optimizes local operation strategies based on real-time data, including adjusting load distribution, optimizing power flow paths, and starting local backup power sources when necessary;

[0151] Collaboration with the central control system: The edge computing unit maintains real-time communication with the central control system, and synchronizes data and analysis results in both directions. The central control system pushes macro-level decisions and strategies to the edge computing unit, which then feeds back local real-time analysis results and execution status to ensure the consistency and coordination of the overall power grid operation.

[0152] Dynamic adjustment and execution: Based on the central control system's strategy and real-time analysis results, the edge computing unit dynamically adjusts the operation strategy locally, including adjusting voltage levels and switching power supply paths to cope with emergencies caused by extreme weather. The edge computing unit can respond quickly and effectively slow down the further deterioration of the power grid;

[0153] Recovery and monitoring: Under extreme weather conditions, the edge computing unit continuously monitors the status of the local power grid, dynamically adjusts and optimizes the power grid recovery strategy, and ensures that normal power supply is restored in the shortest time possible. The execution status and effect data of all recovery operations will be synchronously transmitted to the central control system to coordinate the recovery of the entire power grid.

[0154] By deploying edge computing units at key nodes of the power grid, local data can be processed and analyzed in real time, data transmission delays can be reduced, and decision-making speed can be improved. The system can dynamically adjust operating strategies, respond quickly to emergencies, and ensure the consistency and stability of the overall operation of the power grid through real-time collaboration with the central control system. In extreme weather conditions, the module can optimize the power grid's recovery strategy, ensure rapid power supply restoration, and improve the power grid's risk resistance and recovery efficiency.

[0155] Dynamic adjustment and execution include:

[0156] Real-time data monitoring and analysis: The edge computing unit continuously monitors the real-time data of key nodes, including voltage, current, and load changes, and compares and analyzes the strategy data synchronously transmitted by the central control system, expressed as:

[0157] ΔV=V target -V current ;

[0158] Calculate the difference ΔV between the current voltage level and the target voltage, where V target is the target voltage set by the central control system, V current It is the current voltage monitored in real time;

[0159] Dynamic adjustment of voltage level: When the calculated voltage difference ΔV exceeds the predetermined threshold, the edge computing unit immediately performs the voltage adjustment operation. The adjustment strategy can be dynamically adjusted according to the real-time load demand and equipment status, which is expressed as:

[0160] V adjusted =Vcurrent +K·ΔV;

[0161] Among them, V adjusted is the adjusted voltage level, K is the regulation coefficient, ensuring that the regulation amplitude is adapted to the current load conditions;

[0162] Power path switching: Based on the real-time analysis results and the policy guidance of the central control system, when a power path is identified to have a fault or overload risk, the edge computing unit quickly performs the power path switching operation. During the switching process, the shortest path algorithm is used to calculate the alternative path, which is expressed as:

[0163] P new =min(P i ),fori=1,2,…,n;

[0164] Among them, P new is the new power path selected, P i For all the alternative paths with the lowest power loss, the path with the lowest power loss is selected for power switching to minimize the power grid loss and maintain the stability of power supply;

[0165] Quick response and execution: In emergencies caused by extreme weather, the edge computing unit immediately performs the above-mentioned voltage adjustment and power path switching operations. The edge computing unit can respond quickly and effectively mitigate the further deterioration of the power grid. When executing adjustments, the system continuously monitors the adjustment effects and further optimizes the operation strategy based on feedback data.

[0166] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0167] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. Urban distribution network resilience recovery management system under extreme weather conditions, characterized by: It includes data collection and processing module, resilience assessment module, scenario simulation and virtual training module, decision support module, emergency response module, and edge computing and real-time optimization module: The data collection and processing module includes multiple sensors installed at key nodes of the power distribution network to collect voltage, current, temperature, humidity and wind speed in real time, transmit the data to the central control system through a wireless network, clean, format and standardize the data, identify abnormal conditions that affect the stability of the power grid, and fuse the data from different sensors; The resilience assessment module obtains processed data from the data collection and processing module, and combines historical fault data to assess the performance of the power grid under extreme weather conditions, including analysis of the failure risk, recovery capability, and potential weaknesses of the power grid, and establishes a power grid resilience model to predict the impact of future extreme weather events on the power grid and put forward optimization suggestions; The scenario simulation and virtual training module utilizes the power grid resilience model and data provided by the resilience assessment module to simulate various extreme weather scenarios through virtual reality and augmented reality technologies, and conducts virtual drills to verify and optimize response strategies, generate feedback data, and optimize resilience assessment and decision support strategies; The decision support module conducts a comprehensive risk assessment based on the analysis results of the resilience assessment module and the feedback data provided by the scenario simulation and virtual training modules, and generates response strategies, including load transfer, load reduction, and rapid fault repair, and pushes the optimized strategies to the emergency response module for execution; The emergency response module identifies the fault points that need emergency treatment based on the strategies provided by the decision support module, dispatches repair resources, and communicates with the on-site repair team in real time; The edge computing and real-time optimization module deploys edge computing units at key nodes of the power grid to process and analyze local data in real time. The edge computing units work in coordination with the central control system to dynamically optimize the operation strategy of the power grid through real-time analysis results.

2. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The data collection and processing module includes: Sensor data collection: Multiple sensors are installed at key nodes of the distribution network to collect voltage, current, temperature, humidity and wind speed in real time; Data transmission: The data collected by the above sensors in real time are transmitted to the central control system through a wireless network; Data preprocessing: The central control system preprocesses the received data, including data cleaning, formatting and standardization operations; Abnormal situation identification: Real-time analysis of pre-processed data to identify abnormal situations that affect grid stability, including equipment overheating and line overload; Data fusion: Data from different sensors are fused and processed, and multi-source data are integrated into a single data set through a weighted average algorithm.

3. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The resilience assessment module includes: Data acquisition: Receive processed real-time data from the data collection and processing module, including voltage, current, temperature, humidity and wind speed, and obtain historical fault data; Failure risk assessment: Analyze the received real-time data and historical fault data to assess the failure risk of the power grid under current and predicted extreme weather conditions, and use the probabilistic risk analysis method to calculate the probability of power grid failure P f , by integrating the risks of various fault events, the overall failure risk of the power grid under extreme weather conditions is obtained; Restoration Capacity Assessment: Using the Grid Restoration Time T r and recovery cost C r The recovery time can be determined by the average recovery time of similar events in historical data, and the recovery cost is calculated based on the degree of equipment damage and the repair resource requirements; Weakness analysis: Based on the failure risk and recovery capacity data, potential weak points in the power grid are identified. Cluster analysis and sensitivity analysis are used to identify nodes or devices that are prone to failure in extreme weather. Failure events with similar characteristics in historical failure data are grouped together to determine weak points. Resilience model establishment: Based on the above data and analysis results, a Bayesian network is used to establish a power grid resilience model. The model nodes represent the key components or nodes of the power grid, and the edges represent the dependencies between components and the fault propagation paths. The model predicts the overall performance of the power grid under different extreme weather conditions by calculating the conditional probability of each node; Optimization suggestion generation: Based on the output of the resilience model, suggestions are put forward to optimize the design and operation of the power grid, including equipment reinforcement, backup power configuration and optimization of emergency plans. The optimization suggestions are refined through sensitivity analysis.

4. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The scenario simulation and virtual training module includes: Data and model acquisition: Obtain the grid resilience model and related data from the resilience assessment module, including the results of failure risk, recovery capability and weak point analysis; Scenario setting: Different simulation scenarios are set according to the type of extreme weather; each scenario setting includes weather parameters and initial conditions of the power grid; Virtual reality and augmented reality environment construction: Use virtual reality and augmented reality technologies to create a virtual environment similar to the actual power grid, and input the set scenario parameters into the simulation environment. The system dynamically adjusts the performance of the power grid in the simulation based on the model and data provided by the resilience assessment module; Virtual drills: Run simulation scenarios in a virtual environment, verify the effectiveness of existing response strategies by real-time monitoring of the simulated power grid response, analyze the performance of key nodes, including the response of weak points, and record the operation data of the power grid in the simulation scenario; Feedback data generation: Based on the results of the virtual drill, feedback data is generated. The feedback data includes the performance of the power grid in the simulated scenario, including the time of fault occurrence, fault point distribution, and recovery time; Optimization strategy generation: Utilize the generated feedback data to optimize the response strategies in the resilience assessment module and decision support module. By comparing the strategy effects before and after the simulation, adjust and optimize the strategies for grid operation and recovery.

5. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 4 is characterized in that: The construction of the virtual reality and augmented reality environment includes: Virtual environment construction: Based on the grid resilience model and related data provided by the resilience assessment module, a virtual environment similar to the actual grid structure, equipment layout and operating status is constructed on the virtual reality and augmented reality platforms to simulate the physical characteristics and operating dynamics of the actual grid; Scenario parameter input: input the preset extreme weather scenario parameters into the virtual environment. The scenario parameters include the type, intensity, duration of the extreme weather and the initial operation status of the power grid. After input, the virtual environment simulates the operation status of the power grid under specific conditions. Dynamic Adjustment: During the simulation, the system dynamically adjusts the performance of the virtual grid based on real-time data and model analysis from the resilience assessment module, including changes in grid load, the occurrence and propagation of equipment failures, and the recovery process.

6. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 4 is characterized in that: The virtual exercise includes: Simulation scenario running steps: Run the set extreme weather simulation scenario in the virtual environment constructed by virtual reality and augmented reality; Real-time monitoring step: During the simulation scenario operation, the response of each key node in the virtual power grid is monitored in real time, including voltage fluctuations, load changes and equipment failures. The system records the operation status of the power grid through real-time data streams and monitoring interfaces; Response strategy verification step: During the simulation run, verify the effectiveness of the currently applied response strategy, and evaluate the execution effect of the strategy under different conditions by monitoring the performance of each key node, including the impact on grid stability and resilience; Key node analysis step: Detailed analysis of the key nodes of the power grid in the simulation, focusing on the response of the weak points, including analyzing the fault occurrence time, impact range and recovery time of the weak points in the simulation scenario, and identifying the strategies or nodes that need to be improved; Operation data recording steps: During the virtual drill, all operation data of the power grid under the simulated scenario are recorded in detail, including: fault occurrence time, fault point location, load transfer situation, recovery time and strategy execution effect.

7. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The decision support module includes: Data integration and analysis: Obtain analysis results from the resilience assessment module, including assessment data on grid failure risk, recovery capabilities, and potential weaknesses; obtain feedback and integrate data from the scenario simulation and virtual training modules, including fault points and recovery time found in the simulation; Risk assessment: Based on the integrated data, a comprehensive risk assessment is conducted, which includes classifying the risk levels of key nodes and components of the power grid, identifying high-risk areas that may cause serious impacts, and determining the overall risk level of the power grid through quantitative analysis; Strategy generation: Based on the risk assessment results, generate response strategies for different scenarios, including: Load transfer strategies: Identify feasible load transfer paths to relieve pressure on high-risk areas; Load reduction strategy: In extreme cases, the stability of the core area of ​​the power grid is protected by appropriately reducing non-critical loads; Fault fast repair strategy: Determine the optimal fault repair path and resource allocation plan to minimize the overall impact of the fault on the power grid; Strategy optimization: Utilize the feedback data provided by the scenario simulation and virtual training modules to optimize the initially generated response strategies. By comparing the execution effects of the strategies under different simulation scenarios, adjust and improve the strategy parameters and execution plans. Strategy push and execution: Push the optimized response strategy to the emergency response module. The push includes sending specific operation instructions to the on-site repair team and real-time monitoring and adjustment through the central control system.

8. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The emergency response module includes: Fault point identification: Receive the optimization strategy provided by the decision support module, automatically identify the fault points in the power grid that need to be urgently handled based on the analysis results and priorities in the strategy, determine the key fault areas based on real-time data monitoring and strategy guidance, and use them as repair targets; Repair resource scheduling: After the fault point is identified, the system automatically dispatches appropriate repair resources, including maintenance personnel, equipment, tools and spare parts. According to the severity and location of the fault, the system optimizes resource allocation; Real-time communication and coordination steps: The system establishes a real-time communication link with the on-site repair team through the wireless communication network, transmits detailed information of the fault point, repair strategy and required resource list to the on-site team, and continuously monitors the repair progress. The system can also dynamically adjust the repair strategy based on on-site feedback; Repair work monitoring steps: During the repair process, the emergency response module monitors the progress of the repair work in real time, collects on-site repair data, and synchronizes data with the decision support module. The system adjusts the strategy in a timely manner according to the progress of the repair to deal with unexpected situations; Repair completion confirmation step: After the fault repair is completed, the system conducts a final inspection of the fault point to confirm whether the repair meets the expected results, and feeds back the repair completion status information to the central control system, recording the detailed data of the repair work.

9. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 1 is characterized in that: The edge computing and real-time optimization module includes: Edge computing unit deployment: Edge computing units are deployed at key nodes of the power grid. The computing units have independent data processing and computing capabilities, and receive and process data from sensors in real time locally, including voltage, current, and temperature. Local data processing: The edge computing unit processes the collected local data in real time, including data cleaning, anomaly detection, and preliminary analysis; Real-time analysis and optimization: The edge computing unit analyzes the processed data in real time, evaluates the current grid operation status, and dynamically optimizes local operation strategies based on real-time data, including adjusting load distribution, optimizing power flow paths, and starting local backup power sources when necessary; Collaborate with the central control system: The edge computing unit maintains real-time communication with the central control system, and synchronizes data and analysis results in both directions. The central control system pushes macro-level decisions and strategies to the edge computing unit, and the edge computing unit feeds back local real-time analysis results and execution status. Dynamic adjustment and execution: Based on the central control system's strategy and real-time analysis results, the edge computing unit dynamically adjusts the operation strategy locally, including adjusting voltage levels and switching power paths, to cope with emergencies caused by extreme weather; Recovery and monitoring: Under extreme weather conditions, the edge computing unit continuously monitors the status of the local power grid, dynamically adjusts and optimizes the power grid recovery strategy, and the execution status and effect data of all recovery operations will be synchronously transmitted to the central control system.

10. The urban distribution network resilience recovery management system under extreme weather conditions according to claim 9 is characterized in that: The dynamic adjustment and execution include: Real-time data monitoring and analysis: The edge computing unit continuously monitors the real-time data of key nodes, including voltage, current, and load changes, and compares and analyzes the strategy data synchronously transmitted by the central control system; Dynamic adjustment of voltage level: When the calculated voltage difference ΔV exceeds the predetermined threshold, the edge computing unit immediately performs the voltage adjustment operation, and the adjustment strategy is dynamically adjusted according to the real-time load demand and equipment status; Power path switching: Based on real-time analysis results and the policy guidance of the central control system, when a power path is identified to have a fault or overload risk, the edge computing unit quickly performs the power path switching operation. During the switching process, the shortest path algorithm is used to calculate the alternative path and select the path with the least loss for power switching to minimize the loss of the power grid and maintain the stability of power supply. Quick response and execution: In emergencies caused by extreme weather, the edge computing unit immediately performs the above-mentioned voltage adjustment and power path switching operations. The edge computing unit responds quickly and effectively mitigates the deterioration of the power grid. When executing adjustments, the system continuously monitors the adjustment effects and optimizes the operation strategy based on feedback data.

Images