An intelligent power supply planning method based on medium-voltage distribution network

Abstract

The present invention proposes an intelligent power supply planning method based on a medium-voltage distribution network. The method includes: constructing a digital twin model based on preprocessed data; generating an adaptive dynamic clone model pool to monitor future load changes and equipment status of the power grid, and at the same time coping with different power grid operating conditions and emergencies; performing load prediction and power supply strategy simulation according to the real-time status data output by the clone model pool and the digital twin model, and selecting the optimal strategy to cope with various possible power grid operating conditions and emergencies; combining the results of multimodal load prediction and the priority ranking calculated according to the comprehensive score; executing the optimal power supply strategy and performing real-time monitoring, and dynamically adjusting the strategy parameters when executing the strategy; implementing fault prediction and self-healing mechanisms according to the real-time monitoring and feedback data. The present invention provides an intelligent, dynamic and integrated solution, laying a foundation for the development of future smart power grids.

Description

Technical Field

[0001] The present invention belongs to the technical field of medium - voltage distribution networks, and particularly relates to an intelligent power supply planning method based on a medium - voltage distribution network. Background Art

[0002] The medium - voltage distribution network is an important part of the power system, responsible for transmitting electric energy from the high - voltage grid to the low - voltage distribution network and ultimately to the user side. With the acceleration of urbanization and the continuous increase in power demand, the structure and operating environment of the medium - voltage distribution network have become increasingly complex. This complexity is reflected in the following aspects: First, the medium - voltage distribution network has a wide coverage area, numerous lines and nodes, and significant differences in load characteristics in different regions, with frequent and unpredictable load fluctuations. Second, with the access of distributed energy resources (DERs) and the increase in the proportion of renewable energy generation, the operating characteristics of the medium - voltage distribution network have become further complicated, which poses higher requirements for power supply stability and power quality. Traditional medium - voltage distribution network power supply planning methods mainly rely on static models and pre - set scheduling strategies, and these methods have obvious deficiencies in dealing with load fluctuations and faults.

[0003] The existing technologies mainly use fixed scheduling strategies or static optimization methods based on historical data for power supply planning. These methods face multiple challenges in practical applications. First, traditional methods lack the dynamic response ability to real - time load and network state changes and cannot adapt to rapidly changing load demands and network topologies in a timely manner. This lag is likely to lead to problems such as local overload, voltage deviation, and low power supply efficiency. Second, due to the variety of equipment and complex operating environment in the medium - voltage distribution network, it is difficult for traditional static planning methods to accurately predict and respond to equipment failures and emergencies. Third, with the progress of information and communication technologies, although some systems have introduced data - driven prediction and optimization methods, these systems usually rely on a large amount of labeled data for training, with high data acquisition costs and limited model generalization ability, making it difficult to adapt to the constantly changing distribution network environment. In addition, existing technologies often lack a unified and intelligent power supply management platform to integrate various types of information and optimization strategies, thus making it difficult to achieve global optimization and intelligent management of the medium - voltage distribution network.

[0004] Therefore, in the current technical situation, how to effectively improve the real - time performance, reliability, and efficiency of medium - voltage distribution network power supply planning has become an urgent problem to be solved. Summary of the Invention

[0005] The object of the present invention is to design an intelligent power supply planning method based on a medium-voltage distribution network, namely an intelligent power supply planning method for a medium-voltage distribution network based on an adaptive dynamic cloning model and digital twin technology. Through the collection and analysis of real-time data, this method adaptively generates an optimal power supply strategy model, and uses digital twin technology for accurate simulation and optimization, which can significantly improve the response ability and operation efficiency of the medium-voltage distribution network in a complex environment.

[0006] To achieve the above object, the present invention provides an intelligent power supply planning method based on a medium-voltage distribution network, and the method includes the following steps:

[0007] Step 1: Collect data in real time and perform preprocessing, and construct a digital twin model according to the preprocessed data; specifically including the following steps;

[0008] S11: Install intelligent sensors at key nodes of the medium-voltage distribution network to collect multi-modal parameters of the power grid in real time;

[0009] S12: Use the exponential weighted moving average algorithm to smooth the time series data of the multi-modal parameters;

[0010] S13: Construct a digital twin model according to the smoothed data;

[0011] S14: Use the Kalman filter algorithm to correct the digital twin model by combining the predicted state and actual observation data;

[0012] Step 2: Generate an adaptive dynamic cloning model pool according to the state data output by the digital twin model, predict the future load changes and equipment status of the power grid, and at the same time cope with different power grid operation conditions and emergencies; specifically including the following steps:

[0013] S21: Extract features from the state data output by the digital twin model to obtain feature vectors;

[0014] S22: Construct multiple prediction models, design a cloning model pool containing multiple prediction models, where each prediction model is used for prediction under a specific load pattern or state, and then define multiple prediction models as linear regression models for initialization to make a preliminary prediction of the power grid load;

[0015] S23: When multiple prediction models are initialized, design an adaptive weight update algorithm based on real-time feedback to dynamically predict the weights and biases of each model, so that it can better predict the actual power grid load;

[0016] S24: Design a weighted strategy based on error to select the most suitable model for the current state or fuse the prediction results of multiple models;

[0017] Step 3: Based on the real-time status data output by the cloned model pool and the digital twin model, conduct load prediction and power supply strategy simulation. Meanwhile, by combining the real-time power grid status, predicting future load changes and equipment status, simulate different power supply strategies and select the optimal strategy to cope with various possible power grid operating conditions and emergencies. Specifically, it includes the following steps:

[0018] S31: Use each prediction model in the cloned model pool to predict the load at future moments based on the state feature vectors output by the digital twin model, and obtain the multi-modal load prediction results;

[0019] S32: Introduce an adaptive regularization term in the prediction to control the response of each prediction model to the changes in the power grid status;

[0020] S33: Construct a dynamic model integration strategy with a fluctuation adjustment coefficient, and adapt to the dynamic changes of the power grid by adjusting the weights of each prediction model;

[0021] S34: Integrate the future loads of each prediction model, simulate multiple power supply strategies in the digital twin model and conduct simulations in the digital twin model, calculate the simulation outputs of each strategy at the next moment, and calculate the comprehensive score based on multiple evaluation indicators. Select the strategy with the highest comprehensive score as the power supply strategy for actual execution;

[0022] Step 4: Combine the multi-modal load prediction results and the priority ranking calculated according to the comprehensive score, and continue to optimize the power supply strategy to ensure the efficient and stable operation of the power grid under complex load conditions. Specifically, it includes the following steps:

[0023] S41: Define an objective optimization function based on minimizing power supply losses, maximizing voltage stability and minimizing equipment overload according to the multi-modal load prediction results and the priority ranking calculated according to the comprehensive score;

[0024] S42: Introduce a scheduling constraint term in the multi-modal load prediction results and the priority ranking calculated according to the comprehensive score to ensure that the optimal scheduling scheme is considered when generating the power supply strategy;

[0025] S43: Combine the objective optimization function and the scheduling constraint term to obtain an optimization problem;

[0026] S44: Design an adaptive optimization algorithm to dynamically adjust according to the real-time status of the power grid and the load prediction, and obtain the optimal power supply strategy;

[0027] Step 5: Execute the optimal power supply strategy and conduct real-time monitoring, feedback the monitoring results, and dynamically adjust the strategy parameters during the execution of the strategy to ensure the accuracy of the strategy execution and the stable operation of the power grid. Specifically, it includes the following steps:

[0028] S51. Set initial parameters for the current real-time sensor data and execute the execution plan of the initial parameters as the optimal power supply strategy;

[0029] S52. During the process of strategy execution, the real-time monitoring system monitors the key parameters of the power grid, transmits the real-time collected data to the central control system to compare with the predicted strategy execution results, calculates the execution error, and makes real-time corrections by adjusting the initial parameters according to the magnitude and direction of the execution error to obtain the strategy parameters;

[0030] S53. During the process of strategy execution, introduce a dynamic evaluation mechanism to conduct real-time evaluation on the overall operation status of the power grid to obtain the evaluation results;

[0031] Step Six. Implement a fault prediction and self-healing mechanism based on the real-time monitored and feedback data; specifically including the following steps:

[0032] S61. Construct a multi-level dynamic prediction model, take the features extracted from the real-time data as input, and conduct fault prediction;

[0033] S62. Add an adaptive anomaly detection algorithm to the fault prediction, compare the historical state and the current state of each node of the power grid to identify possible fault modes; once the fault probability of a certain node or multiple nodes is detected to exceed the preset threshold, the self-healing mechanism will be immediately activated; the adaptive anomaly detection algorithm includes a predefined set of self-healing strategies, and each strategy corresponds to a specific type of fault response;

[0034] S63. Combine the fault response time, recovery cost, and power grid stability to design a multi-objective optimization problem for the self-healing strategy, calculate the priority score of each self-healing strategy, evaluate the comprehensive effect of each strategy, sort all self-healing strategies according to the priority score, and select the strategy with the highest score as the final executed self-healing measure;

[0035] S64. After selecting the optimal self-healing strategy, immediately execute the strategy to restore the normal operation of the power grid, simultaneously monitor the real-time state of the power grid, evaluate the effect of the self-healing strategy, and make necessary strategy adjustments according to the feedback;

[0036] S65. Automatically enter a closed-loop optimization process after each fault event is processed, and update the multi-level dynamic prediction model and the set of self-healing strategies by analyzing the effect of each self-healing and the efficiency of the system response.

[0037] Furthermore, the digital twin model is used to describe the dynamic behavior of the medium-voltage distribution network, including:

[0038] Construct a state space model to represent the digital twin model, and the state space model uses a state vector to represent the system at time The global state, including voltage and current information of all nodes, simulates and predicts changes in the power grid state by constructing a state space model.

[0039] Further, the S23 is specifically expressed as follows:

[0040] When new data arrives, recalculate the prediction error of each prediction model and adjust the weight of the model according to the error, which is expressed as follows:

[0041]

[0042] where is the updated weight vector, is the current weight, is the learning rate, is the actual load value, is the predicted value of the model;

[0043] By continuously adjusting the weights, each prediction model can be optimized under various load patterns and adapt to different operating states.

[0044] Further, the S24 is specifically expressed as follows:

[0045] First, calculate the prediction error of each prediction model. The prediction deviation is the square difference between the actual load and the predicted value;

[0046] Then, based on the prediction deviation, calculate the weight factor of each model. The weight factor of each model is used to fuse the prediction results of multiple models;

[0047] Finally, dynamically adjust the influence of the model through the weight factor, and synthesize the predictions of each model to obtain a more accurate final predicted value.

[0048] Further, the second step further includes:

[0049] Introduce an online adaptation and expansion mechanism. When the system detects that the prediction error continuously exceeds the preset threshold within a certain period of time, it means that the existing clone model pool cannot adapt to the current power grid state. Then, automatically generate a new prediction model and add it to the clone model pool. The new prediction model is initialized based on the parameters of the current optimal model and is adjusted through online learning to adapt to the new load pattern.

[0050] Further, the adaptive regularization term includes a penalty term and adjustments to the current load volatility and historical data of the power grid, which is expressed as follows:

[0051] ,

[0052] where represents the regularization term, which is used to capture the volatility of the power grid state; represents the number of power grid nodes; represents the node weight, which controls the contribution of the volatility of each node to the overall regularization; and respectively represent the voltage and current of the th node; and respectively represent the historical average voltage and current of the th node, which are used to calculate the deviation degree of the current state.

[0053] Furthermore, the objective optimization function based on minimizing power supply loss, maximizing voltage stability, and minimizing equipment overload is expressed as follows:

[0054] ,

[0055] where represents the comprehensive optimization objective of the power supply strategy ; respectively represent the weight coefficients of the objective function, reflecting the importance of each index; n represents the total number of nodes; t represents the current moment; represents the power loss of node under the strategy ; represents the voltage of node under the strategy ; represents the reference voltage value, which is used to measure voltage stability; represents the load of node under the strategy ; represents the maximum allowable load of the node, which prevents equipment overload.

[0056] Furthermore, the S44, design an adaptive optimization algorithm to dynamically adjust according to the real-time state of the power grid and load prediction, specifically including:

[0057] Combining the particle swarm optimization and the Lagrangian relaxation method to balance the relationship between the objective function and the constraints. In each iteration, the algorithm updates the position and velocity of the particles, and at the same time adjusts the Lagrange multipliers to relax the scheduling constraints to obtain the optimal power supply strategy, which is expressed as follows:

[0058] ,

[0059] where represents the power supply strategy of the th iteration; represents the power supply strategy of the th iteration; represents the learning rate, which is used to control the step size of each update; represents the power supply strategy gradient; represents the Lagrange multiplier, which adjusts the relaxation degree of different scheduling strategies; represents the optimization objective of the power supply strategy at the iteration; represents the scheduling constraint term; P represents the total scheduling strategy; represents under the power supply strategy the scheduling result of the represents the expected scheduling result of the

[0060] Further, the dynamic evaluation mechanism is expressed as follows:

[0061] ,

[0062] where represents the overall evaluation value of the current policy execution; represents the weights of different operation metrics, which control the influence of each metric on the overall evaluation;

[0063] If the evaluation function does not reach the preset target value, the policy parameters will be automatically recalculated, and enter the next round of policy execution and adjustment loop until the evaluation function reaches the ideal level.

[0064] Further, the adaptive anomaly detection algorithm is constructed as follows:

[0065] Set a dynamic fault prediction metric , evaluate the fault probability of each node, and use the Bayesian update mechanism combined with the Markov chain Monte Carlo method to calculate the fault probability, which is expressed as follows:

[0066] ,

[0067] where represents the fault probability at time ; represents the conditional likelihood function, which represents the likelihood of observing the feature vector under the execution parameter ; represents the prior probability, which represents the prior knowledge of the fault at time ; represents the marginal probability of the feature vector ;

[0068] Combining the fault response time, recovery cost, and power grid stability, design a multi-objective optimization problem for the self-healing strategy, and calculate the priority score of each self-healing strategy, which is expressed as follows:

[0069] ,

[0070] where represents the priority score of the self-healing strategy ; represents the response time of strategy , and the shorter it is, the better; represents the recovery cost of strategy ; represents the influence function of strategy on the power grid stability, and the higher it is, the better; represents the priority weight coefficient, which is used to balance the influence of different objectives;

[0071] Sort all self-healing strategies according to the priority score and select the strategy with the highest score as the final self-healing measure to be executed.

[0072] The beneficial technical effects of the present invention are at least as follows:

[0073] By introducing an adaptive dynamic cloning model, the present invention uses machine learning algorithms to automatically generate and adjust load prediction and power supply strategy models under different operating scenarios according to real-time data. This model can adaptively clone and optimize strategies, dynamically respond to the actual operating state of the distribution network, and effectively solve the problems of frequent load fluctuations and the inability of traditional methods to respond in real time. Through online learning and continuous optimization, the model can still maintain efficient and reliable power supply planning in a complex and changeable environment.

[0074] By constructing a digital twin model of the medium-voltage distribution network, the present invention can reflect the physical state and operating parameters of the distribution network in real time, and achieve precise simulation and global optimization of the entire power grid. Digital twin technology can integrate multi-source data and dynamically update the model state, enabling the optimization of power supply strategies not only based on current data, but also on the simulation and verification of future states, ensuring the optimality and stability of power supply schemes under various complex conditions. Compared with traditional static models, the digital twin model provides a real-time and dynamic global perspective, which can better handle emergencies such as equipment failures and load mutations in the medium-voltage distribution network, and achieve rapid response and self-healing.

[0075] The present invention proposes an integrated intelligent power supply management platform. Combining an adaptive dynamic cloning model and digital twin technology, this platform can perform intelligent management throughout the entire process from data collection, load prediction, strategy simulation to power supply optimization. Through real-time monitoring and feedback control, the platform can continuously optimize the power supply strategy to maximize power supply efficiency and security. At the same time, the system has emergency response and self-healing functions, and can quickly execute emergency strategies when faults or abnormalities occur, reducing the duration and scope of power outages. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] The present invention will be further described with reference to the accompanying drawings. However, the embodiments in the drawings do not constitute any limitation to the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on the following drawings without creative efforts.

[0077] Figure 1 It is a flowchart of an intelligent power supply planning method based on a medium-voltage distribution network according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0078] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are only used to explain the present invention and should not be construed as a limitation to the present invention.

[0079] In one or more embodiments, as Figure 1 shown, an intelligent power supply planning method based on a medium-voltage distribution network according to the present invention is disclosed. The method includes steps 1 to 6, including:

[0080] Step 1: Collect data in real time and perform preprocessing, and construct a digital twin model based on the preprocessed data.

[0081] Specifically, install intelligent sensors at key nodes (such as substations, distribution lines, switchgear) of the medium-voltage distribution network to collect parameters such as voltage, current, power, and temperature of the power grid in real time. The data of each node includes multiple dimensions: , where represents the node number, represents the time. The data collected by the sensors is updated once per second, forming a time series data set.

[0082] Among them, the data of all nodes is collected once per second, forming a real-time data matrix:

[0083] ,

[0084] Here, represents all nodes at time The sensor data matrix where $n$ is the number of nodes. This data is the basic input of the digital twin model, reflecting the current state of the distribution network.

[0085] Furthermore, to ensure data accuracy and eliminate noise, it is necessary to preprocess the data of each node. Specifically, sensor data may contain noise or outliers, which can affect the accuracy of the model. To smooth the data and eliminate short-term fluctuations, the Exponentially Weighted Moving Average (EWMA) is used to smooth the time series data:

[0086] ,

[0087] In this formula, represents the smoothed data of node at time , is the smoothing coefficient (e.g., 0.3), which is used to control the weights of recent data and historical data. This preprocessing can reduce the short-term fluctuations of the data, highlight the long-term trends, and make the model input data more stable. The smoothed data will be used as the input for the next step of the model.

[0088] Furthermore, the construction of the digital twin model is to use the preprocessed data to construct a State Space Model (SSM), which is used to describe the dynamic behavior of the medium-voltage distribution network. The core of the state space model is to use the state vector to represent the global state of the system at time , including the voltage and current information of all nodes. By constructing the state space model, the changes in the grid state can be simulated and predicted. The system state update equation is:

[0089] ,

[0090] Here, represents the state vector (such as voltage and current) at the next time step, is the state transition matrix, which describes how the current state affects the state at the next time step; is the control input matrix, which represents the impact of external control actions (such as load adjustment) on the system state; is the control input vector, is the system noise (assumed to be Gaussian white noise), which represents the unmeasured disturbances in the power grid. This model is used to capture the dynamic changes of the system state over time and predict the future grid state.

[0091] Furthermore, to ensure that the digital twin model can accurately reflect the actual power grid state, the Kalman filter algorithm is used for real-time state estimation and correction. The Kalman filter is a recursive algorithm that corrects the model by combining the predicted state and actual observation data. The update formula of the Kalman filter is:

[0092]

[0093] In this formula, is the corrected state estimate at time , is the prior state estimate, which is the predicted value based on the state update equation. is the Kalman gain, which is used to determine how to adjust the estimate value, is the actual observation vector (such as power and temperature obtained from sensors), is the observation matrix that maps the state vector to the observation space. Through this step, the present invention can continuously adjust the model state according to real-time observation data, reduce prediction errors, and improve model accuracy.

[0094] Furthermore, at each time step, the digital twin model uses the above formula for state update and estimate correction to ensure that the state vector and the estimated error covariance of the model are consistent with the dynamic behavior of the actual distribution network. The output of the model, including the latest state estimate and the error covariance matrix, provides an accurate data basis for subsequent load prediction and power supply optimization. The model is updated once per second to reflect the state changes of the distribution network in real time.

[0095] In this step, the digital twin model realizes high-precision and dynamic simulation of the medium-voltage distribution network state by integrating real-time collected data, data preprocessing, and state space modeling, combined with the Kalman filter algorithm. This real-time updated model provides a reliable basis for subsequent load prediction and optimization.

[0096] Step 2: Generate an adaptive dynamic clone model pool based on the state data output by the digital twin model to predict the future load changes and equipment states of the power grid, and at the same time cope with different power grid operating conditions and emergencies.

[0097] Specifically, an adaptive dynamic clone model pool is generated from the real-time state data output by the digital twin model constructed in step 1. This model pool aims to predict future load changes and equipment status of the power grid to cope with different power grid operating conditions and emergencies. Considering the complexity and dynamic changes of the medium-voltage distribution network, the present invention designs an adaptive mechanism to enable these models to continuously adjust according to real-time data, improving the accuracy and adaptability of predictions. The core of this step is to maintain the stability and reliability of power grid operation through online learning and dynamic updating of the models, providing accurate inputs for subsequent power supply optimization strategies.

[0098] Specifically, in step 1, the present invention has constructed a digital twin model capable of real-time updating, and the output state estimation vector and error covariance matrix reflect the current dynamic behavior of the power grid. These data provide real-time state information of each node (such as substations, lines) of the power grid, including voltage, current, etc.

[0099] To generate an adaptive dynamic clone model, the present invention first needs to extract key feature vectors from these outputs , which contain important state information of each node. These features are used to describe the overall state of the power grid and provide inputs for the prediction model. For example, if the state estimation contains voltage and current information of

[0100] nodes, the present invention can define the feature vector as:

[0101] Here, and represent the voltage and current of node at time . In this way, the present invention obtains a feature representation of the current state of the power grid, and these features will be used as inputs for the clone model.

[0102] Furthermore, after extracting the state features, the present invention needs to construct multiple prediction models to adapt to different power grid states. Considering the diversity of power grid load and operating states, the present invention designs a clone model pool containing multiple models . Each model is used for prediction under specific load patterns or states.

[0103] Initially, each model in the model pool is defined as a simple linear regression model for preliminary prediction of the power grid load. The mathematical representation of these models is:

[0104] ,

[0105] In this formula, represents the model for predicting the load at the next moment, is the weight vector of the model, and is the bias. Each model is set according to different initial conditions to capture different load patterns. Through this structure, the present invention can use multiple models to run in parallel to preliminarily predict different load changes.

[0106] Furthermore, once the clone model pool is initialized, the present invention needs to ensure that these models can dynamically adapt to the actual situation of the power grid. The present invention designs an adaptive weight update algorithm based on real-time feedback to adjust the weights and biases of each model so that it can better predict the actual power grid load.

[0107] Specifically, when new data arrives, the present invention calculates the prediction error of each model and adjusts the weights of the model according to this error:

[0108] ,

[0109] Here, is the updated weight vector, is the current weight, is the learning rate, is the actual load value, is the predicted value of the model. By continuously adjusting the weights, each model can be optimized under various load patterns and adapt to different operating states. This adaptive update mechanism enables the model to continuously learn and adapt to the dynamic changes of the power grid.

[0110] To improve the accuracy of the overall prediction, the present invention needs a strategy to select the most suitable model for the current state or fuse the prediction results of multiple models. The present invention uses a weighted strategy based on error to achieve this.

[0111] First, calculate the prediction error of each model , which is the squared difference between the actual load and the predicted value:

[0112] ,

[0113] Then, based on these errors, the present invention calculates the weight factor of each model , and these weight factors are used to fuse the prediction results of multiple models:

[0114] ,

[0115] Among them, is a smoothing parameter used to control the impact of errors on the weights. Through this weighting strategy, the present invention can dynamically adjust the influence of the model and synthesize the predictions of each model to obtain a more accurate final prediction value :

[0116] ,

[0117] This fusion strategy allows the system to adjust the contributions of each model according to the real-time prediction performance, ensuring the best prediction results under different grid states.

[0118] Furthermore, the load patterns and states of the power grid may change significantly over time and with the environment. Therefore, relying solely on the existing model pool may not be sufficient to handle all situations. To improve the flexibility and adaptability of the system, the present invention introduces an online adaptation and extension mechanism.

[0119] When the system detects that the prediction error continuously exceeds the preset threshold within a certain period of time, it means that the existing model pool cannot well adapt to the current grid state. At this time, the system automatically generates a new model , and adds it to the model pool. The new model can be initialized based on the parameters of the current optimal model and further adjusted through online learning to adapt to the new load pattern.

[0120] This mechanism ensures the dynamic scalability and continuous optimization ability of the model pool, can respond to changes in the grid state in real time, and ensures the prediction accuracy and reliability of the system.

[0121] Through this solution, the process of generating the preliminary adaptive dynamic cloning model is systematically designed as a series of steps from data extraction, model construction, parameter update, model selection to online adaptation and extension. Each step closely depends on the output of the previous step and ensures that the model can be dynamically adjusted and extended to adapt to the complex and changing medium-voltage distribution grid state.

[0122] Step 3: According to the real-time state data output by the cloned model pool and the digital twin model, conduct load prediction and power supply strategy simulation. At the same time, by combining the real-time grid state, predicting future load changes and equipment states, simulate different power supply strategies and select the optimal strategy to cope with various possible grid operating conditions and emergencies.

[0123] Specifically, use the adaptive dynamic cloning model for load prediction. The inputs are the adaptive dynamic cloning model pool obtained from Step 2 and the state feature vector output by the digital twin model in Step 1 :

[0124] First, use each model in the cloned model pool Predict the load at a future time. Each model makes predictions based on previously adjusted weights and biases to make predictions. These parameters are continuously optimized during the model update process to adapt to different grid states. The load prediction formula is:

[0125] ,

[0126] where represents the prediction of the load at the next time step by model . represents the weight vector of the model, indicating the influence weight of grid characteristics on the load. represents the feature vector at the current time step, including status information such as voltage and current at each node. represents the bias term, indicating the basic prediction value of the model. represents the adjustment coefficient, dynamically adjusting the sensitivity of the model to perturbations in the prediction. represents the regularization term, indicating the volatility of the grid state. The output of the model is smoothed through this term to prevent overfitting.

[0127] To improve the robustness of the model under complex and changing grid states, the present invention introduces an adaptive regularization term to control the response of the model to changes in the grid state. This regularization term is not only a simple penalty term but also includes adjustments to the current load volatility and historical data of the grid, making the model more sensitive to abnormal data or rapid changes.

[0128] ,

[0129] where represents the regularization term for capturing the volatility of the grid state. represents the number of grid nodes. represents the node weight, controlling the contribution of the fluctuation of each node to the overall regularization. and represent the th node's voltage and current. and represent the historical average voltage and current of the th node, used to calculate the deviation from the current state.

[0130] To further improve the prediction accuracy, the present invention adopts an innovative dynamic model integration strategy. This strategy not only considers the historical performance of each model but also dynamically adjusts the model weights through the newly introduced fluctuation adjustment coefficient to adapt to the dynamic changes of the grid;

[0131] ,

[0132] Among them, represents the integrated weight of the model at time . represents the smoothing factor, which adjusts the influence of the model error on the weight. represents the model at time prediction error. represents the fluctuation adjustment coefficient, which controls the adjustment range of the grid volatility on the weight. represents the variance of the grid load fluctuation, indicating the uncertainty of the current grid state. This strategy can better reflect the contributions of different models to the prediction at different times by adjusting the weight in real time, thus improving the overall accuracy and robustness of the load prediction.

[0133] Furthermore, based on the future load predicted by the integrated model , the present invention simulates multiple power supply strategies in the digital twin model. The strategy set , each strategy represents a different power supply method, such as load reallocation, transformer tap adjustment, or standby power source activation.

[0134] Perform simulations in the digital twin model, calculate the simulation output of each strategy at the next moment , and calculate the comprehensive score based on multiple evaluation indicators (such as voltage stability, power loss, equipment load rate) and express it as:

[0135] ,

[0136] Among them, represents the comprehensive score of the strategy . represents the weight of the th evaluation indicator, indicating the importance of this indicator in the overall score. represents the function of the th evaluation indicator, calculating the performance of the strategy simulation output under this indicator.

[0137] Finally, select the strategy with the highest comprehensive score as the power supply strategy actually implemented:

[0138] ,

[0139] This selection ensures the optimal performance of the grid operation under the current and predicted load conditions.

[0140] Through this detailed process, combined with an innovative load prediction model and strategy simulation method, the present invention can accurately predict the future power grid state and select the optimal solution among different power supply strategies. This process provides crucial support for the intelligent management of the power grid, ensuring efficient and stable power supply in a complex and changing power grid environment.

[0141] Step 4: Continuing to optimize the power supply strategy by combining the multi-modal load prediction results and the priority ranking calculated according to the comprehensive score to ensure the efficient and stable operation of the power grid under complex load conditions.

[0142] Specifically, first determine the optimization objectives and constraints. The input is the accurate load prediction output in Step 3 and the priority of the scheduling strategy . These data provide the load information of the power grid at future moments and the scheduling strategies to be executed preferentially.

[0143] The present invention defines an optimization objective function , which is used to measure the overall performance of the power supply strategy . The optimization objectives include three core parts: minimizing power supply losses, maximizing voltage stability, and minimizing equipment overload. The objective function is defined as:

[0144] ,

[0145] where represents the comprehensive optimization objective of the power supply strategy . represents the weight coefficient of the objective function, reflecting the importance of each index. represents the power loss of node under strategy . represents the voltage of node under strategy . represents the reference voltage value, which is used to measure voltage stability. represents the load of node under strategy . represents the maximum allowable load of the node to prevent equipment overload.

[0146] To further optimize the flexibility and adaptability of the power supply strategy, the present invention introduces an innovative scheduling constraint term , which combines the predicted load and the information of the scheduling strategy priority . It ensures that the optimal scheduling scheme is considered when generating the power supply strategy:

[0147] ,

[0148] Among them, represents the scheduling constraint item, reflecting the consistency between the power supply strategy and the scheduling strategy. represents the weight of the scheduling strategy adjustment, controlling the priority between different strategies. represents under the power supply strategy , the -th scheduling result of the scheduling strategy. represents the -th expected scheduling result of the scheduling strategy.

[0149] Furthermore, combining the objective function and the scheduling constraint item , the total optimization problem is defined as:

[0150] ,

[0151] Among them, represents the weight coefficient of the scheduling constraint, used to control the consistency between the power supply strategy and the scheduling strategy.

[0152] The goal of this optimization problem is to generate a power supply strategy under the given load prediction and scheduling strategy priority, so that the overall operation performance of the power grid is optimal, and there is a high consistency between the power supply strategy and the scheduling strategy.

[0153] Furthermore, to solve the above optimization problem, the present invention designs an adaptive optimization algorithm, which can be dynamically adjusted according to the real-time state of the power grid and the load prediction. The core idea of the algorithm is to combine Particle Swarm Optimization (PSO) and Lagrangian Relaxation to balance the relationship between the objective function and the constraints.

[0154] In each iteration, the algorithm updates the position and velocity of the particles, and at the same time adjusts the Lagrange multiplier to relax the scheduling constraint:

[0155] ,

[0156] Among them, represents the power supply strategy of the -th iteration. represents the power supply strategy of the -th iteration. represents the learning rate, used to control the step size of each update. represents the gradient of the power supply strategy . Denote the Lagrange multiplier, which adjusts the relaxation degree of different scheduling strategies. Through this adaptive optimization process, the present invention can effectively generate an optimal power supply strategy , ensuring the operation efficiency and stability of the power grid under complex load conditions.

[0157] Through this detailed step, combined with the innovative optimization objective and scheduling constraint design, the present invention provides a complete and innovative solution for power supply strategy generation, ensuring that the power grid can dynamically adapt to various complex operating conditions and maintain efficient and stable power supply. Each step makes full use of the output of the previous step and provides a solid foundation for subsequent actual implementation.

[0158] Step 5: Execute the optimal power supply strategy and conduct real-time monitoring, feedback the monitoring results, and dynamically adjust the strategy parameters during strategy execution to ensure the accuracy of strategy execution and the stable operation of the power grid.

[0159] Specifically, the optimized power supply strategy output in step 4 . This strategy contains specific operation instructions for each node (such as load transfer, transformer regulation, switch operation, etc.) and is the optimal solution generated based on the current power grid state and predicted load.

[0160] Before strategy execution, set initial parameters according to the current real-time data The execution parameters serve as the execution plan of the strategy , and the specific form is:

[0161] ,

[0162] wherein, represents the execution parameters of the strategy and is the instruction set for actual operation. represents the adjustment step size, which is used to ensure the stability and flexibility of execution. represents the gradient of the optimization objective function with respect to the strategy, which is used to correct the execution direction of the initial strategy.

[0163] During the execution of the initial strategy, by adjusting the step size and gradient correction, the strategy execution can better meet the actual power grid requirements and avoid strategy deviation caused by inaccurate initial settings.

[0164] Furthermore, during the process of strategy execution, the operating state of the power grid will constantly change. Therefore, the present invention needs to continuously monitor the key parameters of the power grid (such as voltage , current , load , etc.) through a real-time monitoring system. The real-time monitoring data represented by the following matrix:

[0165] ,

[0166] The monitoring system will transmit the real-time collected data to the central control system for comparison with the expected policy execution results.

[0167] Furthermore, in order to ensure the accuracy of policy execution, the present invention designs an adjustment mechanism based on feedback control. Specifically, the present invention will monitor the real-time data and the expected results of policy execution to calculate the execution error ;

[0168] ,

[0169] wherein, represents the execution error matrix, reflecting the difference between the actual execution result and the expectation. represents the expected execution result of the policy which is based on the prediction data during policy optimization.

[0170] According to the magnitude and direction of the error matrix , the policy parameters are adjusted in real time. The adjustment formula is as follows:

[0171] ,

[0172] wherein, represents the feedback control coefficient, controlling the sensitivity of error adjustment. represents the corrected execution parameter, which is the actual instruction for policy execution in the next time step.

[0173] Through this adjustment mechanism, the system can dynamically correct the policy during policy execution, ensuring that the actual execution effect is consistent with the optimization result, thereby guaranteeing the stable operation of the power grid.

[0174] Furthermore, during policy execution, the present invention introduces a dynamic evaluation mechanism to evaluate the overall operation status of the power grid in real time. The present invention uses the following evaluation function to judge the effectiveness of the current policy execution:

[0175] ,

[0176] wherein, represents the overall evaluation value of the current policy execution. represents the weights of different operation indicators, controlling the influence of each indicator on the overall evaluation.

[0177] If the evaluation function does not reach the preset target value, the system will automatically recalculate the policy parameters and enter the next round of policy execution and adjustment loop until the evaluation function reaches the ideal level or the system runs stably.

[0178] Furthermore, during the policy execution and adjustment process, the present invention sets multiple termination conditions, such as: the grid operation state reaches stability, the error is reduced to an acceptable range, the evaluation function reaches the preset target, etc. Once any termination condition is met, the policy execution and adjustment process ends, and the grid enters the stable operation state.

[0179] Meanwhile, the system will save the policy parameters executed this time and relevant data to provide reference data for the next round of optimization and execution, ensuring the continuous optimization and improvement of the system.

[0180] Step Six: Implement a fault prediction and self-healing mechanism based on the real-time monitoring and feedback data.

[0181] Specifically, according to the real-time monitoring feedback data of Step Five and the corrected execution parameters . These data include the real-time status information of key grid parameters such as voltage, current, and load.

[0182] Then, in order to achieve high-precision fault prediction, the present invention constructs a multi-level dynamic prediction model and continuously evaluates the grid state using real-time data. First, extract key features for fault prediction:

[0183] ,

[0184] Among them, represents the fault prediction feature vector, which includes the voltage , current , load and their change rates of all nodes;

[0185] Among them, , represents the voltage and current change rates of node at time .

[0186] Furthermore, in order to achieve high-precision prediction of grid faults, the present invention adopts an adaptive anomaly detection algorithm This algorithm is based on a step-by-step learning approach, comparing the historical and current states of each node in the power grid to identify possible fault patterns.

[0187] Set a dynamic fault prediction index , which is used to evaluate the fault probability of each node. The present invention uses a Bayesian update mechanism combined with the Markov Chain Monte Carlo (MCMC) method to calculate the representation of the fault probability

[0188] ,

[0189] where, represents the fault probability at time . represents the conditional likelihood function, indicating the likelihood of observing the feature vector under the execution of the parameter . represents the prior probability, indicating the prior knowledge of the fault at time . represents the marginal probability of the feature vector .

[0190] Estimate the conditional likelihood and marginal probability through the MCMC sampling method, and gradually update the fault probability of each node to achieve dynamic monitoring of potential faults.

[0191] Furthermore, once the fault probability of a certain node or multiple nodes exceeds the preset threshold , the system will immediately activate the self-healing mechanism . This mechanism includes a set of predefined self-healing strategies , and each strategy corresponds to a specific type of fault response.

[0192] To determine the optimal self-healing strategy, the present invention designs a multi-objective optimization problem, comprehensively considering the fault response time, recovery cost, and power grid stability. Define the self-healing priority score function , and evaluate the comprehensive effect of each strategy as follows:

[0193] ,

[0194] where, represents the priority score of the self-healing strategy . represents the response time of the strategy , and the shorter the better. represents the recovery cost of the strategy , and the lower the better. represents the influence function of the strategy on the power grid stability, and the higher the better. Represents the priority weight coefficient, which is used to balance the impacts of different objectives.

[0195] According to the priority score Sort all self-healing strategies and select the strategy with the highest score As the final self-healing measure to be executed:

[0196] ,

[0197] Furthermore, select the optimal self-healing strategy After that, the system immediately executes this strategy, and quickly restores the normal operation of the power grid by adjusting switches, transferring loads, activating backup power supplies, etc. During the execution process, the system continuously monitors the real-time state of the power grid, evaluates the effect of the self-healing strategy, and makes necessary strategy adjustments according to the feedback.

[0198] To further improve the self-healing efficiency, the system adopts an adaptive update mechanism. According to the real-time feedback data and the failure probability update , dynamically adjust the self-healing strategy parameters to ensure that the power grid can quickly recover and operate stably after a failure occurs.

[0199] Furthermore, to continuously improve the performance of the fault prediction and self-healing mechanism, the system automatically enters a closed-loop optimization process after each fault event is processed. By analyzing the effect of each self-healing and the efficiency of the system response, update the fault prediction model and the self-healing strategy library to achieve more accurate prediction and faster response to future faults.

[0200] During each optimization process, the system adjusts the model parameters and strategy parameters to ensure that the fault prediction and self-healing mechanism can self-improve and gradually enhance the stability and security of the power grid.

[0201] These are only some preferred embodiments of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. A smart power supply planning method based on a medium voltage distribution network, characterized in that: The method comprises the following steps: Step 1: Collect data in real time and perform preprocessing, and build a digital twin model based on the preprocessed data; specifically, the following steps are included: S11. Install smart sensors at key nodes of the medium voltage distribution network to collect multi-modal parameters of the power grid in real time; S12, using an exponentially weighted moving average algorithm to smooth the time series data of the multimodal parameters; S13, constructing a digital twin model based on the smoothed data; S14. Use the Kalman filter algorithm to correct the digital twin model by combining the predicted state and actual observation data; Step 2: Generate an adaptive dynamic clone model pool based on the state data output by the digital twin model to predict future load changes and equipment status of the power grid, and respond to different power grid operating conditions and emergencies; specifically, the following steps are included: S21. Extract features from the state data output by the digital twin model to obtain a feature vector; S22, construct multiple prediction models, design a clone model pool containing multiple prediction models, wherein each prediction model is used for prediction under a specific load mode or state, and then define the multiple prediction models as linear regression models for initialization to make a preliminary prediction of the load of the power grid; S23. When multiple prediction models are initialized, an adaptive weight update algorithm based on real-time feedback is designed to dynamically predict the weight and bias of each model, so that it can better predict the actual grid load; S24. Design an error-based weighting strategy to select the model that best suits the current state or fuse the prediction results of multiple models; Step 3: Based on the real-time status data output by the clone model pool and the digital twin model, load forecasting and power supply strategy simulation are performed. At the same time, by combining the real-time grid status, predicting future load changes and equipment status, different power supply strategies are simulated, and the optimal strategy is selected to deal with various possible grid operating conditions and emergencies; specifically, the following steps are included: S31. Use each prediction model in the clone model pool to predict the load at a future moment according to the state feature vector output by the digital twin model to obtain a multimodal load prediction result; S32, introducing an adaptive regularization term in the prediction to control the response of each prediction model to changes in the power grid state; S33, construct a dynamic model integration strategy that introduces fluctuation adjustment coefficients, and adapt to the dynamic changes of the power grid by adjusting the weight of each prediction model; S34, integrating the future load of each prediction model, simulating multiple power supply strategies in the digital twin model and simulating in the digital twin model, calculating the simulation output of each strategy at the next moment, and calculating the comprehensive score based on multiple evaluation indicators, and selecting the strategy with the highest comprehensive score as the power supply strategy actually implemented; Step 4: Combine the multi-modal load forecast results and the priority ranking calculated based on the comprehensive score to continue optimizing the power supply strategy to ensure that the power grid operates efficiently and stably under complex load conditions; specifically, the following steps are included: S41, defining an optimization function based on the objectives of minimizing power supply loss, maximizing voltage stability, and minimizing equipment overload according to the multimodal load prediction results and the priority ranking calculated according to the comprehensive score; S42, introducing scheduling constraints into the multimodal load forecast results and the priority ranking calculated based on the comprehensive score, to ensure that the optimal scheduling scheme is considered when generating the power supply strategy; S43, combining the target optimization function and the scheduling constraint item to obtain an optimization problem; S44, design an adaptive optimization algorithm to dynamically adjust according to the real-time state of the power grid and load forecast to obtain the optimal power supply strategy; Step 5: Execute the optimal power supply strategy and conduct real-time monitoring, provide feedback on the monitoring results, and dynamically adjust the strategy parameters when executing the strategy to ensure the accuracy of strategy execution and the stable operation of the power grid; specifically, the following steps are included: S51, setting initial parameters for current real-time sensor data, and executing the initial parameters as an execution plan for the optimal power supply strategy; S52. During the execution of the strategy, the real-time monitoring system monitors the key parameters of the power grid, transmits the real-time collected data to the central control system, compares it with the predicted strategy execution results, calculates the execution error, and adjusts the initial parameters to make real-time corrections according to the size and direction of the execution error to obtain the strategy parameters; S53. During the strategy execution process, a dynamic evaluation mechanism is introduced to evaluate the overall operation status of the power grid in real time and obtain evaluation results; Step 6: Implement fault prediction and self-healing mechanisms based on real-time monitoring and feedback data; specifically, the following steps are included: S61, construct a multi-level dynamic prediction model, using the features extracted from real-time data as input to perform fault prediction; S62, adding an adaptive anomaly detection algorithm to fault prediction, comparing the historical state and current state of each node in the power grid, and identifying possible fault modes; once it is detected that the fault probability of a node or multiple nodes exceeds a preset threshold, the self-healing mechanism will be immediately started; the adaptive anomaly detection algorithm includes a set of predefined self-healing strategies, each strategy corresponding to a specific type of fault response; S63. Combining fault response time, restoration cost and grid stability, design a multi-objective optimization problem for self-healing strategies, calculate the priority score of each self-healing strategy, evaluate the comprehensive effect of each strategy, sort all self-healing strategies according to the priority score, and select the strategy with the highest score as the self-healing measure to be finally executed; S64. After selecting the optimal self-healing strategy, immediately execute the strategy to restore the normal operation of the power grid, monitor the real-time status of the power grid, evaluate the effect of the self-healing strategy, and make necessary strategy adjustments based on feedback; S65. After each fault event is handled, a closed-loop optimization process is automatically entered to update the multi-level dynamic prediction model and self-healing strategy set by analyzing the effect of each self-healing and the efficiency of the system response.

2. According to claim 1, a smart power supply planning method based on a medium voltage distribution network is characterized in that: The digital twin model is used to describe the dynamic behavior of the medium voltage distribution network, including: A state space model is constructed to represent the digital twin model. The state space model uses a state vector to represent the global state of the system at a moment, including the voltage and current information of all nodes. By constructing the state space model, the changes in the power grid state can be simulated and predicted.

3. According to claim 1, a smart power supply planning method based on a medium voltage distribution network is characterized in that: The S23 is specifically expressed as follows: When new data arrives, the prediction error of each prediction model is recalculated, and the weight of the model is adjusted according to the prediction error, as shown below: ， in, is the updated weight vector, is the current weight, is the learning rate, is the actual load value, is the model's predicted value, is the key feature vector; By continuously adjusting weights, each prediction model can be optimized under various load modes and adapt to different operating conditions.

4. According to claim 3, a smart power supply planning method based on a medium voltage distribution network is characterized in that: The S24 is specifically expressed as follows: First, the prediction error of each prediction model is calculated, where the prediction error is the square difference between the actual load and the predicted value; Then, based on the prediction error, a weight factor of each model is calculated, and the weight factor of each model is used to fuse the prediction results of multiple models; Finally, the influence of the model is dynamically adjusted through the weight factor, and the predictions of each model are combined to obtain a more accurate final prediction value.

5. The intelligent power supply planning method based on the medium voltage distribution network according to claim 1 is characterized in that: The step 2 further includes: An online adaptation and expansion mechanism is introduced. When the system detects that the prediction error continues to exceed the preset threshold for a period of time, it means that the existing clone model pool cannot adapt to the current power grid status. Then a new prediction model is automatically generated and added to the clone model pool. The new prediction model is initialized based on the parameters of the current optimal model and adjusted through online learning to adapt to the new load pattern.

6. The intelligent power supply planning method based on the medium voltage distribution network according to claim 1 is characterized in that: The adaptive regularization term is , Including penalty terms, adjustments to the current load volatility of the power grid and historical data, it is expressed as follows: ， in, represents the regularization term, which is used to capture the volatility of the power grid state; Indicates the number of grid nodes; Represents the node weight, which controls the contribution of each node's fluctuation to the overall regularization; and Respectively represent The voltage and current of each node; and Respectively represent The historical average voltage and current of each node are used to calculate the deviation of the current state.

7. The intelligent power supply planning method based on the medium voltage distribution network according to claim 1 is characterized in that: The objective optimization function based on minimizing power loss, maximizing voltage stability and minimizing equipment overload is expressed as follows: ， in, Indicates the power supply strategy Comprehensive optimization goal; They represent the weight coefficients of the objective function, reflecting the importance of each indicator; n represents the total number of nodes; t represents the current time; Indicated in strategy Next, node Power loss; Indicated in strategy Next, node Voltage; Indicates the reference voltage value, used to measure voltage stability; Indicated in strategy Next, node Load; Indicates the maximum allowable load of the node to prevent device overload.

8. The intelligent power supply planning method based on the medium voltage distribution network according to claim 7 is characterized in that: The S44, designing an adaptive optimization algorithm to dynamically adjust according to the real-time state of the power grid and load forecast, specifically includes: Combining particle swarm optimization and Lagrangian relaxation method, the relationship between the objective function and the constraints is balanced. In each iteration, the algorithm updates the position and velocity of the particles and adjusts the Lagrangian multiplier to relax the scheduling constraints to obtain the optimal power supply strategy, which is expressed as follows: ， in, Indicates The power supply strategy for the next iteration; Indicates The power supply strategy for the next iteration; Represents the learning rate, which is used to control the step size of each update; Indicates the power supply strategy The gradient of represents the Lagrange multiplier, which adjusts the relaxation degree of different scheduling strategies; Indicates The optimization goal of the power supply strategy for the next iteration; represents the scheduling constraint; P represents the overall scheduling strategy; Indicates the power supply strategy Next, The scheduling result of a scheduling strategy; Indicates The expected scheduling results of a scheduling strategy.

9. The intelligent power supply planning method based on medium voltage distribution network according to claim 1 is characterized in that: The dynamic evaluation mechanism is expressed as follows: ， in, It represents the overall evaluation value of the current strategy execution; Indicates the weights of different operating indicators and controls the impact of each indicator on the overall evaluation; represents the voltage at node i, represents the current at node i, represents the load of node i, and n represents the total number of nodes; If the overall evaluation value If the preset target value is not reached, the strategy parameters will be automatically recalculated and the next round of strategy execution and adjustment cycle will be entered until the overall evaluation value reaches Reach the ideal level.

10. The intelligent power supply planning method based on medium voltage distribution network according to claim 1, characterized in that: The adaptive anomaly detection algorithm is constructed as follows: Setting a dynamic failure prediction index , evaluate the failure probability of each node, and use the Bayesian update mechanism combined with the Markov chain Monte Carlo method to calculate the failure probability, which is expressed as follows: ， in, Indicates at time The probability of failure at a given moment; Represents the conditional likelihood function, which means that when executing the parameters The observed eigenvector possibility; represents the prior probability and represents the time Prior knowledge of faults at the moment; Represents the feature vector The marginal probability of The multi-objective optimization problem of self-healing strategy is designed by combining fault response time, restoration cost and grid stability, and the priority score of each self-healing strategy is calculated, which is expressed as follows: ， in, Represents a self-healing strategy Priority score; Representation strategy The response time, the shorter the better; Representation strategy the cost of restoration; Representation strategy The impact function on grid stability, the higher the better; Represents the priority weight coefficient, which is used to balance the impact of different goals; All self-healing strategies are sorted according to the priority scores, and the strategy with the highest score is selected as the self-healing measure to be finally executed.

Images