A hierarchical security early warning method based on the simulation of smart grid

Abstract

The present invention relates to the technical field of smart grids, and discloses a hierarchical security warning method based on smart grid simulation. The method includes the following steps: S1, collect the operation data of the smart grid, including real-time monitoring data of voltage, current, power factor, and temperature, and process the collected operation data; S2, use the extended Kalman filter algorithm to optimize the estimation of the grid state; S3, establish a non-linear dynamic model of the smart grid, and predict the health state of the grid according to the dynamic behavior of the grid; S4, construct a Bayesian network model, evaluate the risk of the grid through probability inference, and judge the health condition of the grid. By combining smart grid simulation, deep reinforcement learning, and adaptive optimal control, the present invention realizes the intelligence, adaptive adjustment, and real-time response capabilities of the grid warning system, and improves the stability and emergency response efficiency of the grid in a complex environment.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and particularly to a hierarchical security warning method based on smart grid simulation and emulation. Background Art

[0002] The existing power grid management systems usually adopt a warning mechanism based on manually set thresholds, which can detect some faults and anomalies of the power grid at an early stage and issue alarms. These systems can quickly identify problems and trigger warnings when obvious faults occur in the power grid through real-time monitoring of key parameters, and then take predetermined emergency measures. The traditional monitoring systems also have a relatively mature hardware architecture and a low deployment cost, and are suitable for relatively simple power grid operation environments.

[0003] However, there are some deficiencies in the existing power grid monitoring and warning systems; the existing systems mostly rely on manually set thresholds and lack intelligent dynamic adjustment and real-time evaluation capabilities. Since the threshold setting is static, it cannot adapt to the changes of the power grid in real time. Especially when dealing with complex and sudden power grid risks, it is easy to cause response lags or inaccurate warnings; in addition, the resource scheduling in the emergency response of the existing systems is not flexible enough. It often can only rely on preset rules and lacks the ability to flexibly adjust according to the actual situation of the power grid, which leads to the inability to respond effectively in a timely manner in some complex situations. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technology, the present invention provides a hierarchical security warning method based on smart grid simulation and emulation, which solves the problems that the existing power grid warning systems lack intelligence, adaptive adjustment and real-time response capabilities.

[0005] To achieve the above purposes, the present invention is realized through the following technical solutions: A hierarchical security warning method based on smart grid simulation and emulation, the method includes the following steps:

[0006] S1. Collect the operation data of the smart grid, including real-time monitoring data of voltage, current, power factor and temperature, and process the collected operation data;

[0007] S2. Optimize the estimation of the power grid state by using the extended Kalman filter algorithm;

[0008] S3. Establish a non-linear dynamic model of the smart grid, and predict the health state of the power grid according to the dynamic behavior of the power grid;

[0009] S4. Construct a Bayesian network model, evaluate the risk of the power grid through probability inference, and judge the health status of the power grid;

[0010] S5. Based on the Nash equilibrium model in game theory, synergistically optimize the behaviors of multiple decision-making entities in the power grid, thereby achieving the global stability of the power grid;

[0011] S6. Use the maximum entropy principle in information theory to optimize the setting of warning levels and the information flow transmission strategy, adjust the information distribution and transmission methods of each warning level, and ensure effective information flow;

[0012] S7. Based on adaptive optimal control and deep reinforcement learning, adjust the operation strategy of the power grid in real time and optimize the warning response;

[0013] S8. Automatically trigger hierarchical safety warning responses according to the health status of the power grid and the results of risk assessment.

[0014] Preferably, the optimization of the power grid state estimation using the extended Kalman filter algorithm includes:

[0015] Perform optimal estimation of the non-linear state of the power grid based on the extended Kalman filter (EKF) algorithm;

[0016] Update the health status of the power grid in real time, use the power grid measurement data and dynamic model to correct the prediction of the power grid state, and reduce the influence of noise on the system estimation;

[0017] Adjust the error estimation of the system by calculating the Kalman gain to further improve the accuracy of the power grid state prediction.

[0018] Preferably, the establishment of the non-linear dynamic model of the smart grid includes:

[0019] Use the operation data to construct the state vector of the power grid, and describe the dynamic relationship between the various states of the power grid through non-linear functions;

[0020] Introduce a perturbation term to simulate the influence of external factors on the power grid system, so that the power grid model can better adapt to different operating environments;

[0021] Use Lyapunov stability theory to analyze the stability of the power grid model and ensure that the model remains stable under various perturbations.

[0022] Preferably, the construction of the Bayesian network model includes:

[0023] Construct the Bayesian network of the power grid by establishing the conditional dependence relationship between the various parameters of the power grid;

[0024] Calculate the conditional probability distribution of each node according to the historical operation data of the power grid, and infer its risk probability according to the current state of the power grid;

[0025] Based on the inference results, evaluate the risk level of the power grid under different operating states, and provide decision support for the operation of the power grid through Bayesian inference.

[0026] Preferably, the optimization of the behaviors of multiple decision-making entities in the power grid based on the Nash equilibrium model in game theory includes:

[0027] Set multiple control entities in the power grid, including load dispatching, generator dispatching, and standby power supplies, as the participants in the game;

[0028] Utilize the Nash equilibrium solution to optimize the decisions of each entity through game theory to achieve the globally optimal power grid operation state;

[0029] Each entity adjusts its decision-making behavior according to the health status and risk assessment results of the power grid to ensure the stable operation of the power grid.

[0030] Preferably, the optimization of the setting of warning levels and the information flow transmission strategy using the maximum entropy principle in information theory includes:

[0031] Based on the maximum entropy principle in information theory, by optimizing the information distribution of each warning level in the power grid, the system can quickly transmit risk information;

[0032] Set corresponding information transmission mechanisms for different warning levels to ensure the effectiveness of the information flow;

[0033] Under different risk levels, according to the state and real-time data of the power grid, dynamically adjust the information distribution strategy to reduce redundant information.

[0034] Preferably, the real-time adjustment of the power grid operation strategy based on adaptive optimal control and deep reinforcement learning includes:

[0035] Introduce the deep reinforcement learning (DQN) algorithm, use the real-time data of the power grid to train the intelligent decision-making system, and adaptively adjust the control strategy of the power grid;

[0036] Combine the optimal control theory, and optimize the emergency response mechanism of the power grid by learning the operation mode and risk state of the power grid in real time;

[0037] Through reinforcement learning training, the system can continuously optimize the warning timing and response intensity, reducing false alarms and missed alarms.

[0038] Preferably, the automatic triggering of hierarchical safety warning responses based on the health status and risk assessment results of the power grid includes:

[0039] According to the evaluation results of the power grid health status, automatically select the corresponding warning level, and trigger the warning response through the intelligent decision-making system;

[0040] In high-risk situations, the system can automatically adjust the operation strategy of the power grid, including measures such as enabling standby power supplies and adjusting load distribution;

[0041] In low-risk situations, the system can select a non-intervention response mode to maintain grid stability.

[0042] Preferably, the method for predicting the risk of the power grid based on the power grid simulation model further includes:

[0043] Using a dynamic power grid simulation model, combining historical power grid data and real-time operation data, to predict the potential risks of the power grid from multiple perspectives;

[0044] Through big data analysis technology, simulate and predict the risk scenarios of different fault modes and equipment failures, and identify in advance the security threats that the power grid may face.

[0045] Preferably, the feedback mechanism for the power grid health status and risk assessment results includes:

[0046] Through a real-time monitoring and data feedback system, periodically update the health status of the power grid and the risk assessment results;

[0047] The system continuously adjusts the early warning strategy and response behavior based on the feedback mechanism to ensure that the power grid can flexibly respond to emergencies in different operating environments.

[0048] The present invention provides a hierarchical security early warning method based on intelligent power grid simulation. It has the following beneficial effects:

[0049] 1. Through the automated hierarchical security early warning response mechanism of the present invention, the early warning level is automatically adjusted in real time according to the health status and risk assessment of the power grid. Compared with the traditional manual threshold setting, this intelligent system greatly improves the accuracy and timeliness of early warning, and reduces the false alarms and delays that may be caused by human operations.

[0050] 2. By adopting the technology combining adaptive optimal control and deep reinforcement learning, the power grid can dynamically adjust the dispatching strategy in the face of uncertain load fluctuations and equipment failures. This makes the power grid more flexible and can automatically adapt to real-time changes, avoiding the rigidity and inefficiency of traditional fixed strategies.

[0051] 3. Combining the maximum entropy principle in information theory, the present invention optimizes the information flow transmission and the setting of early warning levels. By reducing the transmission of redundant information, the efficiency of information transmission is improved, ensuring that key early warning information can reach decision-makers quickly, and avoiding the slow response caused by information overload in traditional systems.

[0052] 4. The present invention optimizes the behavior of each decision-making subject of the power grid through the Nash equilibrium model in game theory, avoiding the local optimum problem in traditional management methods. The system can coordinate the decisions of all parties to ensure the global stability of the power grid in a complex environment and the maximum use of resources. Description of the Drawings

[0053] Figure 1 This is the flowchart of the method of the present invention. Specific embodiments

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the specification of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts belong to the scope of protection of the present invention.

[0055] Please refer to the attached Figure 1 , the embodiments of the present invention provide a hierarchical security warning method based on intelligent power grid simulation. The method includes the following steps:

[0056] S1. Collect the operation data of the intelligent power grid, including real-time monitoring data of voltage, current, power factor, and temperature, and process the collected operation data;

[0057] By collecting and processing the operation data of the intelligent power grid, the accuracy of subsequent steps such as dynamic modeling, state estimation, and risk assessment is ensured. The collection and processing of data directly determine the reliability of the entire system warning. In this step, the system comprehensively collects and processes the real-time operation data of the power grid to ensure the quality and consistency of the data. High-quality data is the key to power grid state prediction and security warning. Therefore, the data collection and preprocessing of the power grid are very important.

[0058] In this embodiment, the collection of the operation data of the intelligent power grid mainly involves real-time monitoring data such as voltage, current, power factor, and temperature of the power grid. The system monitors multiple key nodes of the power grid in real time through a sensor network and collects these operation data. In addition, the system also collects data such as historical fault records, equipment status, and maintenance logs of the power grid to provide long-term data support for the operation of the power grid. Through various types of collected data, the system can more comprehensively evaluate the health status of the power grid.

[0059] In this embodiment, data collection is usually achieved through sensors installed at each node of the power grid. These sensors monitor and record various operation parameters of the power grid in real time. Specifically, voltage sensors measure the voltage of each node in the power grid, current sensors measure the current, power factor sensors measure the relationship between the power grid load and the power supply, and temperature sensors monitor the working temperature of power grid equipment (such as transformers, switchgear, etc.). These sensors can continuously and stably collect data and transmit it to the central processing unit of the system through a communication network.

[0060] Specifically, the acquisition of parameters such as voltage, current, power factor, and temperature can be basically calculated through the following formulas:

[0061] ;

[0062] Where: represents the power of the grid node at time (unit: watt); is the voltage value of the grid node at time (unit: volt); is the current value of the grid node at time (unit: ampere); is the phase angle between voltage and current; is the power factor, representing the phase difference between voltage and current.

[0063] This formula shows how to calculate the power of the grid, obtaining the power value through the product of voltage, current, and power factor. The system calculates the power of each node in real time, which is used as an important indicator of the grid health status.

[0064] In the data processing stage after data acquisition, the system preprocesses the data through various methods. First, the system performs noise removal. Due to factors such as sensor errors and electromagnetic interference, the collected signals may contain noise, which will affect the subsequent analysis results. Therefore, it is necessary to remove the noise through filtering algorithms (such as Kalman filtering, mean filtering, etc.) to ensure the accuracy of the data.

[0065] In a possible implementation, the system optimizes and corrects the collected data through the Kalman filtering algorithm. Kalman filtering is a recursive estimation algorithm that can provide the optimal state estimation in an environment with noise. By combining the system model and measurement data, Kalman filtering can effectively filter out external noise and improve the quality of the data.

[0066] For the data processing of the power grid, the core of the Kalman filter is to perform the optimal estimation of the system state through the update equation. The system updates the power grid state through the following formula:

[0067] ;

[0068] Where: is the updated estimated state of the power grid at time ; represents the estimated vector of the power grid state at time (such as voltage, current, power, etc.); is the Kalman gain, and the calculation formula is:

[0069] ;

[0070] Wherein: is the actual measurement data; is the predicted value of the power grid state (calculated by the system model); is the time state estimation covariance matrix; is the covariance of the measurement noise; is the measurement matrix; represents the transpose of the measurement matrix HHH.

[0071] Through this formula, the system can update the state estimation of the power grid according to the new measurement data, reducing the impact of noise on the system estimation.

[0072] Next is outlier detection. Power grid equipment may malfunction or sensors may have problems, resulting in abnormal data. The system needs to detect and exclude these abnormal data to avoid their impact on subsequent decisions. Outlier detection can be done by setting thresholds. For example, if a data value deviates too much from the normal range, it is regarded as an outlier and excluded.

[0073] In this case, the system also needs to perform data normalization. Because the magnitudes of different types of data such as voltage and current vary greatly, if analyzed directly, it may cause some parameters to have too much influence on the final result. By normalizing the data, parameters of different magnitudes can be transformed into a unified standard range, ensuring that each data item has an equal impact on the analysis result.

[0074] For example, assume the voltage value collected by a certain sensor is , and the current value is , then the following normalization formula can be used:

[0075] ;

[0076] Wherein: and are the minimum and maximum values of the voltage data respectively; and are the minimum and maximum values of the current data respectively; are the normalized voltage and current data, with a value range of [0, 1].

[0077] Through normalization, the voltage and current data will be mapped to a unified scale range, making subsequent model analysis more accurate.

[0078] As an option, in some embodiments, the system may also combine time series analysis methods, such as Fourier transform or wavelet transform, to perform frequency domain analysis on the current and voltage waveforms of the power grid and identify the periodic changes existing in the power grid. In this way, the system can effectively identify the vibrations of power grid equipment or the fluctuations of current loads, thereby providing more detailed monitoring of the health status of the power grid.

[0079] Through data cleaning, denoising, outlier detection, and normalization processing, the system can avoid false alarms and missed alarms caused by poor data quality. Through strict data quality management, it provides solid data support for subsequent model prediction, risk assessment, etc.

[0080] S2. Optimize the estimation of the power grid state using the extended Kalman filter algorithm;

[0081] Optimize the state estimation of the power grid through the extended Kalman filter (EKF) algorithm. The Kalman filter can provide the optimal estimation in a data environment containing noise, thereby providing more accurate information for predicting the health status of the power grid.

[0082] In this embodiment, the extended Kalman filter algorithm (EKF) is applied to the non-linear state estimation of the power grid. Since the power grid system is a non-linear dynamic system, the performance of the Kalman filter algorithm in dealing with non-linear systems is more effective than that of the traditional linear Kalman filter. Through the extended Kalman filter, the system can eliminate the influence of noise on state estimation while performing real-time monitoring of the power grid state, and improve the accuracy of state estimation.

[0083] In a possible implementation, the system first predicts the state of the power grid based on the non-linear dynamic model of the power grid. This model describes the relationships between various state variables of the power grid, such as voltage, current, power factor, etc. The model can use the following state update equation:

[0084] ;

[0085] Where: represents the state of the power grid system at time ; is the power grid state vector, which includes state parameters such as voltage, current, power, etc.; is the control input vector, which includes control parameters such as power grid scheduling and load management; is the non-linear function of the power grid system, which describes the dynamic relationship of the power grid state evolving over time; is the random disturbance term of the system, which simulates the influence of external factors on the power grid state, such as equipment failures and environmental changes.

[0086] In this prediction model, the update of the power grid state is jointly determined by the dynamic characteristics of the power grid and the control input, while the influence of external disturbances needs to be considered. Therefore, the system predicts the power grid state through this dynamic model.

[0087] In the update step of the extended Kalman filter, the system uses real-time measurement data to correct the predicted power grid state. Specifically, the system calculates the Kalman gain by comparing the difference between the predicted value and the actual measurement data, and adjusts the estimation of the power grid state through it.

[0088] The calculation of the Kalman gain determines how to combine the measurement data with the prediction data. The larger the Kalman gain, the higher the trust level of the system in the current measurement value.

[0089] Through the weighting of the Kalman gain, the system can effectively fuse the predicted value and the actual measurement data, so as to obtain a more accurate estimation of the power grid state.

[0090] Through this update process, the system can adjust the estimation of the power grid state in real time, gradually correct the prediction error, and improve the accuracy of the state estimation.

[0091] In the extended Kalman filter, the covariance matrix reflects the uncertainty of the system's estimation of the power grid state. By updating the covariance matrix, the system can dynamically adjust the trust levels of prediction and measurement. The covariance matrix update formula is as follows:

[0092] ;

[0093] where: represents the covariance matrix of the updated state estimation at time ; is the covariance matrix of the state estimation at time ; is the identity matrix, used to represent the unit transformation when updating the covariance matrix; is the Kalman gain; is the measurement matrix.

[0094] By updating the covariance matrix, the system can reflect the reliability of the current estimation result and further improve the accuracy of the power grid state estimation.

[0095] Through the extended Kalman filter algorithm, the system can process the nonlinear changes of the power grid state in real time and optimize the estimation of the power grid state in the presence of noise. By combining the measurement data and the prediction model, the extended Kalman filter greatly improves the accuracy of the power grid state estimation. Especially when the power grid faces external disturbances or measurement errors, the extended Kalman filter can effectively reduce the uncertainty and improve the stability and reliability of the system.

[0096] S3. Establish a non - linear dynamic model of the smart grid and predict the health status of the grid according to the dynamic behavior of the grid;

[0097] In step S3, the non - linear dynamic model of the grid is an accurate description of the complex behavior of the grid. The state of the grid usually changes over time, including various key parameters such as voltage, current, power, etc. The relationships between these states are non - linear and cannot be simply described by linear equations. Therefore, non - linear dynamic equations must be used to accurately simulate the changes of the grid.

[0098] Generally, the non - linear dynamic equations of the grid can be constructed by considering the interactions of various state parameters of the grid, control inputs (such as load scheduling, standby power control), and external disturbances (such as equipment failures, environmental factors, etc.).

[0099] The non - linear dynamic characteristics of the grid are manifested in many aspects, such as the relationship between voltage and current, the dependence relationship between power and load, etc. To accurately describe these relationships, the system uses non - linear equations to simulate the state evolution of the grid. For example, the relationship between voltage, current, and power can be represented by a non - linear function in the following form:

[0100] ;

[0101] Where: represents the non - linear dynamic evolution of the power grid system at time and describes the change of the grid state over time; is the state vector of the grid at time ; is the control input vector, which includes external factors or operation instructions that affect the grid state; represents the non - linear dynamic evolution function of the th state variable in the grid; n represents the number of state variables in the grid, that is, the dimension of the grid.

[0102] The dynamic behavior of the grid is not only affected by control inputs, but may also be affected by external disturbances. External disturbances include factors such as equipment failures, sudden load increases, and weather changes. These factors are usually unpredictable, so a disturbance term needs to be added to the model to simulate these effects.

[0103] In some embodiments, the disturbance term can be modeled by a stochastic process, such as a Gaussian noise model:

[0104] ;

[0105] Where: Denote at time the external disturbance term, which usually represents factors such as equipment failures, grid load changes, or environmental interferences; Denote a Gaussian noise with a mean of 0 and a variance of The variance controls the intensity of the disturbance.

[0106] The introduction of such random disturbance terms makes the model more realistic and can take into account various uncertainties that the power grid may encounter during actual operation.

[0107] To ensure the stability of power grid state estimation, the system applies Lyapunov stability theory to analyze the stability of the power grid model. Lyapunov functions are usually used to evaluate the stability of a system when it is subject to disturbances. In the dynamic model of the power grid, the Lyapunov function can be defined as:

[0108] ;

[0109] where: is the Lyapunov function, representing the energy of the power grid state or the system stability; is the state vector of the power grid, containing key state parameters of the power grid (such as voltage, current, etc.); is a positive definite matrix, usually defined according to the characteristics of the power grid. It is used to describe the stability of the system; is the transpose of the power grid state vector to ensure that the Lyapunov function is a scalar; This is a quadratic form expression, representing the specific form of the Lyapunov function.

[0110] The core of Lyapunov stability analysis is to judge whether the system is stable by calculating the derivative of the Lyapunov function. If the derivative is less than zero, it indicates that the power grid system is stable under external disturbances; if it is greater than zero, the system may be unstable. Therefore, the derivative of the Lyapunov function provides important information about the system stability.

[0111] To further improve the prediction accuracy of the power grid state, the system can use machine learning methods to optimize the nonlinear dynamic model. For example, by using techniques such as support vector machines (SVM) or deep neural networks (DNN), training the model with historical data, and automatically optimizing the parameters of the power grid dynamic model, thereby enhancing the adaptability and accuracy of the power grid model.

[0112] Specifically, machine learning methods can help the system automatically identify the complex relationships between power grid states and control inputs, reduce the complexity of manual modeling, and at the same time improve the prediction ability of the model.

[0113] By introducing a non - linear dynamic model, the system can more accurately simulate the actual behavior of the power grid. Especially when facing complex factors such as load fluctuations, equipment failures, and environmental changes, the non - linear model can provide more accurate power grid state predictions. The introduced disturbance term and Lyapunov stability analysis ensure the robustness and stability of the power grid model, enabling it to maintain a high prediction accuracy in an environment with strong uncertainties.

[0114] Specifically, by introducing external disturbance simulation, the health state prediction of the power grid is no longer limited to idealized scenarios, but can take into account the uncertainties in actual operation. This makes the health assessment of the power grid more comprehensive and accurate, and can effectively identify potential risks.

[0115] Through Lyapunov stability analysis and disturbance term simulation, the system ensures the stability and robustness of the power grid model. Introducing machine learning methods to optimize the non - linear dynamic model further improves the accuracy of power grid state prediction. Finally, these technologies provide reliable data support for subsequent risk assessment and early warning, ensuring the safety and stability of power grid operation.

[0116] S4. Construct a Bayesian network model to evaluate the risk of the power grid through probability inference and judge the health status of the power grid;

[0117] S4 conducts risk assessment by constructing a Bayesian network model among power grid state variables. A Bayesian network is a graphical model based on probability inference, used to represent the conditional dependencies between random variables, and calculate the risks of the power grid under different operating states through probability inference.

[0118] A Bayesian network uses a directed acyclic graph (DAG) to represent the dependencies between random variables. In the power grid, there may be complex mutual dependencies among state variables, such as the relationships between current, voltage, and power factor. Therefore, through the Bayesian network, the system can efficiently handle these dependencies and perform conditional probability inference.

[0119] The core of the Bayesian network model lies in the calculation of the joint probability distribution. The joint probability distribution of all state variables in the power grid can be represented by the conditional probability distributions of each state variable. Specifically, the joint probability distribution of power grid state variables is represented by the following formula:

[0120] ;

[0121] where: represents the joint probability distribution of the power grid state , reflecting the overall risk of the power grid in different states. The joint probability distribution can help evaluate the overall risk of the power grid state; Represents a specific state variable in the power grid (such as voltage, current, power factor, etc.). These state variables determine the health status of the power grid; Represents the state variable The set of parent nodes of refers to other state variables related to the state variable Represents the conditional probability distribution of the state variable under the condition of the given parent node . The conditional probability distribution of each state variable is estimated through the historical data and real-time data of the power grid, reflecting the risks in different states.

[0122] Each node in the Bayesian network represents a power grid state variable. The conditional probability distribution of each state variable can be learned through historical data or estimated through existing power grid physical models. For example, the conditional probability distribution of voltage may depend on current and power factor , that is:

[0123] ;

[0124] Where: Represents the conditional probability distribution of voltage under the condition of known current and power factor ; is the voltage state variable in the power grid, reflecting the voltage health status of the power grid; and : The current and power factor state variables in the power grid respectively affect the change of voltage.

[0125] The Bayesian network model calculates the risk of the power grid through inference algorithms. This process usually includes forward inference and backward inference. The goal of inference is to calculate the risks of each state variable of the power grid based on the known data, and then evaluate the overall risk of the power grid.

[0126] Specifically, if the system obtains real-time monitoring data (such as voltage, current, etc.), the Bayesian inference algorithm will update the probability distribution of the power grid state based on these data and calculate the risk probability of the power grid. According to the joint probability distribution , the system can evaluate the health status of the power grid and identify potential risks.

[0127] To classify the health status of the power grid, the system divides the risk level of the power grid into multiple levels. By calculating the risk probability of the power grid state, the system can automatically determine the current risk level of the power grid. For example, the risk level of the power grid can be divided into three levels: low risk, medium risk, and high risk. The specific classification criteria are as follows:

[0128] Low risk level: When the risk probability of the power grid is less than 10%, it indicates that the power grid is in normal operation.

[0129] Medium risk level: When the risk probability of the power grid is between 10% and 30%, it indicates that there may be certain risks in the power grid and it needs to be closely monitored.

[0130] High risk level: When the risk probability of the power grid exceeds 30%, it indicates that there are relatively high risks in the power grid and immediate measures need to be taken.

[0131] To ensure the accuracy of power grid risk assessment, the probability distribution in the Bayesian network is learned through historical data and real-time data. Specifically, the system can use methods such as the Expectation-Maximization (EM) algorithm or variational inference for model training to estimate the conditional probabilities between power grid state variables.

[0132] During the reasoning process, the system calculates the overall risk of the power grid based on the existing power grid state (such as voltage, current, power factor, etc.) and the learned probability distribution.

[0133] By using the Bayesian network model for risk assessment, the system can effectively quantify the health status of the power grid and evaluate the risk level of the power grid under different operating conditions. The Bayesian network can take into account the complex relationships between power grid state variables and be updated according to real-time data, thereby providing accurate data support for the early warning response of the power grid.

[0134] S5. Based on the Nash equilibrium model in game theory, collaboratively optimize the behaviors of multiple decision-making entities in the power grid to achieve the global stability of the power grid;

[0135] S5 optimizes the behaviors of multiple decision-making entities (such as load scheduling, generator scheduling, etc.) in the power grid by using the Nash equilibrium model in game theory to achieve the global stability of the power grid. The application of game theory models in the power grid aims to solve the cooperation and conflict problems between multiple decision-making entities and optimize the strategies of each entity, so that the power grid can maintain stable and efficient operation under different operating conditions.

[0136] The Nash equilibrium in game theory refers to a situation in a multi-decision-making agent system where, when all decision-making agents choose their strategies, no single decision-making agent can improve its payoff by unilaterally changing its strategy. The actions of each decision-making agent affect the others, so the system needs to achieve a balance on a global scale to ensure the optimal strategies of all agents.

[0137] The actions of each decision-making agent can be represented by a set of strategies. Suppose there are decision-making agents in the power grid, and each decision-making agent chooses a strategy , and the combination of strategies of all agents is denoted as .

[0138] Each decision-making agent in the power grid has a payoff function (or utility function) to evaluate the result of choosing a certain strategy given the strategies of other agents. The payoff function of each decision-making agent can be expressed as:

[0139] ;

[0140] where: : represents the payoff or utility of decision-making agent when choosing strategy given the strategies of other decision-making agents ; is the strategy of decision-making agent , representing different operations or actions that the decision-making agent can choose. In the power grid, the strategy of load scheduling may be the load distribution plan, and the strategy of generator scheduling may be the power generation adjustment plan; is the combination of strategies of all decision-making agents in the power grid, representing the set of behavioral decisions of all agents; is the payoff function of decision-making agent .

[0141] The basic definition of the Nash equilibrium is: in a game, if the strategy of each decision-making agent is optimal (i.e., changing its own strategy will not result in a higher payoff when the strategies of other decision-making agents remain unchanged), then this strategy combination is the Nash equilibrium. The specific mathematical expression is:

[0142] ;

[0143] where: represents the optimal strategy of each decision-making agent in the Nash equilibrium state; represents the combination of strategies of all decision-making agents in the power grid; represents the payoff of decision-making agent under a certain strategy combination.

[0144] Specifically, when the strategies of all decision-making entities reach Nash equilibrium, the behaviors of each decision-making entity in the power grid will not result in better outcomes due to a single entity unilaterally changing its strategy. Therefore, the power grid is in a stable state.

[0145] The Nash equilibrium in game theory needs to be solved through optimization algorithms. Optimization algorithms (such as gradient descent, genetic algorithms, simulated annealing, etc.) can be used to solve the optimal strategies of each decision-making entity. Through continuous iteration, the strategies of the decision-making entities will gradually adjust until Nash equilibrium is reached.

[0146] As an option, we can use global optimization methods such as simulated annealing to repeatedly try different strategy combinations, gradually approaching the optimal solution, thereby obtaining the globally optimal stable state of the power grid.

[0147] In the power grid, the behaviors of multiple decision-making entities may interact with each other. For example, the decision on load scheduling may affect the strategy of generator scheduling, and vice versa. The game theory model optimizes the strategies of each decision-making entity, enabling the power grid to maintain stability in the face of different operating states.

[0148] The goal of load scheduling may be to minimize load fluctuations and power grid operating costs.

[0149] The goal of generator scheduling may be to schedule the operation of generators according to the power grid load demand to ensure the stability and optimal allocation of power supply.

[0150] By solving the Nash equilibrium of the game model, the system can achieve the coordination of the behaviors of these different decision-making entities, avoiding local optimality from affecting the overall stability of the power grid.

[0151] Through the Nash equilibrium model in game theory, the system can, while evaluating the power grid risks, optimize various scheduling decisions of the power grid to ensure that the power grid can respond quickly and restore stability in the face of emergencies. For example, the power grid may face situations such as sudden load increase and generator failure. Through the decision-making mechanism optimized by game theory, the power grid can intelligently schedule generators and loads to minimize the system risks and ensure the stability of power supply.

[0152] Specifically, through this game optimization mechanism, load scheduling and generator scheduling can optimize resource allocation and control strategies without sacrificing the stability of the power grid, thereby improving the operating efficiency and emergency response ability of the power grid.

[0153] By optimizing the behaviors of multiple decision-making entities in the power grid based on the Nash equilibrium of game theory, the system can effectively avoid the conflict between local decisions and global goals, ensuring the global stability of the power grid. The Nash equilibrium model enables multiple decision-making entities to coordinate and cooperate to jointly optimize the operating state of the power grid, thereby reducing the uncertainties and risks in power grid operation and ensuring the safe, stable, and efficient operation of the power grid.

[0154] Specifically, the game theory optimization mechanism can:

[0155] Coordinate the behaviors of different decision-making entities (such as load scheduling, generator scheduling, etc.), and avoid the overall instability caused by local optimal solutions;

[0156] Improve the emergency response ability of the power grid to ensure that the power grid can quickly return to stability in the event of an emergency;

[0157] Optimize resource allocation, reduce the operating cost of the power grid, and improve the overall efficiency.

[0158] By constructing a game model and solving the Nash equilibrium, the system can optimize decisions such as load scheduling and generator scheduling to ensure the efficient operation of the power grid. This method provides a strong theoretical basis and technical support for the intelligent scheduling and safety management of the power grid.

[0159] S6. Optimize the setting of warning levels and the information flow transmission strategy in information theory, adjust the information distribution and transmission methods of each warning level to ensure effective information flow;

[0160] The maximum entropy principle is used to optimize the setting of power grid warning levels and the information flow transmission strategy. By maximizing the uncertainty of the system under known constraints, this principle maximizes the effective transmission of information in different risk scenarios, avoids the transmission of redundant information, and optimizes the response ability of the power grid system.

[0161] The core idea of the maximum entropy principle is to optimize the information flow by selecting the probability distribution that can maximize the information uncertainty. The application of this principle can optimize the distribution of warning levels and effectively transmit key information, reducing information overload and delay.

[0162] Information entropy Measures the uncertainty of information, or the redundant part that may exist in information transmission. In the power grid warning system, the magnitude of entropy reflects the efficiency and accuracy of information transmission. The maximum entropy principle requires selecting the probability distribution with the maximum entropy under known constraints, so that the system can transmit as much information as possible while avoiding redundancy.

[0163] The information entropy calculation formula is as follows:

[0164] ;

[0165] Where: Represents the entropy of the power grid warning information, measuring the total uncertainty of the information. If the information entropy in the system is relatively high, it means that the amount of information contained in the system is relatively large, the uncertainty is relatively high, and the efficiency and diversity of information transmission are also relatively large; Represents the warning information item Probability distribution. Different early warning information items represent different power grid risk states, indicating the probability of these risk information occurring; indicating the information item The amount of information. The amount of information is inversely proportional to the probability of an event occurring. The smaller the probability, the larger the amount of information. Through entropy calculation, the system can quantify the possibility of different power grid states and effectively allocate information of different early warning levels.

[0166] By calculating the maximum entropy, the system can ensure that the most valuable information is transmitted in the power grid's early warning mechanism, avoiding redundant transmission of useless information.

[0167] In the process of power grid risk assessment, the system will dynamically set different early warning levels according to the real-time health status of the power grid. Each early warning level represents the response level of the power grid in a certain risk state and is matched with the health index and risk probability of the power grid.

[0168] The principle of maximum entropy optimizes the setting of early warning levels through the following formula:

[0169] ;

[0170] where: represents the early warning level at time . The early warning level of the power grid is dynamically set based on the risk assessment results and information entropy value to ensure that the early warning response can target the actual risk state of the power grid; represents the power grid risk assessment result at time , which may include the health index of the power grid, the probability of various risks, etc. The power grid risk assessment result is the key basis for adjusting the early warning level; represents the information entropy at time , measuring the redundancy and amount of information of the power grid early warning information. A higher entropy value means a higher uncertainty of the power grid state and the need to transmit more risk information in a timely manner.

[0171] By maximizing the information entropy, the system can optimize information allocation, giving priority to transmitting important and urgent risk information to relevant decision-making entities to ensure that the power grid's early warning mechanism is both efficient and accurate.

[0172] To improve the transmission efficiency of power grid early warning information, the system uses the principle of maximum entropy to optimize the transmission strategy of information flow. The optimization of information flow not only improves the speed at which decision-making entities receive early warning information but also ensures the accuracy of the information.

[0173] The information flow rate ( ) is a measure of the information transmission efficiency in the power grid. The information flow rate calculation formula is as follows:

[0174] ;

[0175] Where: represents the information flow at time , measuring the transmission efficiency of information in the power grid. The larger the information flow, the more efficient the information transmission; represents the information item 's probability distribution, indicating the importance or urgency of this information item; represents the information item 's transmission time or propagation speed. This parameter reflects the transmission delay of information and is usually affected by the power grid communication network and information channels.

[0176] The system dynamically optimizes the transmission path of the information flow through the maximum entropy principle, ensuring that when an abnormality occurs in the power grid, information can be transmitted to the relevant decision-making entities quickly and accurately, reducing information delay and redundancy, and enhancing the power grid's emergency response ability.

[0177] By introducing the maximum entropy principle, the system can effectively optimize the setting of the warning level and precisely adjust the transmission strategy of the information flow. Specifically, the maximum entropy optimization mechanism can bring the following advantages:

[0178] By maximizing the information entropy, the system ensures that critical information can be transmitted first, avoiding information redundancy and overload.

[0179] The system can dynamically adjust the warning level according to the health status and risk assessment of the power grid, ensuring that the power grid can make the most appropriate response when facing different risk levels.

[0180] By optimizing the transmission path of the information flow, the system ensures that power grid managers can obtain the most critical information in the shortest time, thus making decisions quickly.

[0181] By calculating the information entropy and dynamically adjusting the distribution and transmission of warning information, the system can effectively improve the efficiency and accuracy of the power grid's emergency response. The application of the maximum entropy principle provides an efficient optimization scheme for the risk management of the power grid, helping to reduce the transmission of redundant information in the event of an emergency and ensuring that the most critical risk information can be transmitted in a timely manner, thus guaranteeing the safe and stable operation of the power grid.

[0182] S7. Based on adaptive optimal control and deep reinforcement learning, adjust the operation strategy of the power grid in real time and optimize the warning response;

[0183] By introducing adaptive optimal control and deep reinforcement learning (DRL), the aim is to enable the power grid to dynamically adjust the operation strategy according to real-time data. This strategy can effectively cope with uncertain load fluctuations, faults of power grid equipment and other emergencies, and optimize the performance and stability of the power grid. The relevant formulas and parameters will be described in detail below.

[0184] The optimization objective function used in the operation of the power grid by adaptive optimal control is usually expressed as a cost function or a performance function. Its main purpose is to adjust the control strategy in real time through a feedback mechanism to ensure the optimal operating state of the power grid. The optimization objective can be expressed as the following integral formula:

[0185] ;

[0186] Where: represents the optimization objective, that is, the integral of the power grid operation cost or system efficiency. Usually, the goal is to minimize this value; is the state vector of the power grid at time , which contains key information of the power grid, such as voltage, current, load, etc.; is the state penalty matrix, which reflects the impact of the power grid state on the cost and is usually used to emphasize the importance of certain key states (such as voltage, current); is the control input vector, which contains the dispatching strategies of the power grid, such as generator dispatching, load dispatching, etc.; is the control input penalty matrix, which reflects the impact of the control strategy on the cost or efficiency of the power grid operation and is often used to adjust the cost of control actions.

[0187] This optimization objective aims to minimize the operation cost and maintain the stability and efficiency of the power grid. Specifically, adaptive optimal control optimizes the operating state of the power grid by adjusting the state vector and the control input .

[0188] Deep reinforcement learning combines the advantages of deep learning and reinforcement learning and can handle high-dimensional complex environments. In power grid dispatching, deep reinforcement learning optimizes the decision-making strategy through environmental feedback. The reinforcement learning model of the power grid is usually expressed as the following Q-learning model:

[0189] ;

[0190] Where: represents the optimal action value function of taking action in state , that is, the long-term return of this decision; represents the state vector of the power grid, which contains various real-time data of the power grid, such as voltage, current, load, etc.; represents the action or control strategy taken in a given state, such as adjusting the load, starting the standby power supply, etc.; represents the immediate reward, which is usually related to the goodness of the power grid operation state, cost savings, stability, etc.; is the discount factor, which controls the degree to which the control system values future rewards. The larger the discount factor, the stronger the system's focus on long-term goals; is the current action is the next state reached by the power grid after represents all possible actions in the new state under

[0191] Specifically, in the operation of the power grid, the deep reinforcement learning model continuously adjusts the scheduling strategy through a combination of exploration and exploitation to maximize long-term benefits and ensure the efficient and stable operation of the power grid.

[0192] The combination of adaptive optimal control and deep reinforcement learning enables the power grid to adapt to changing load demands and emergencies in real time. Generally, these two methods play their respective advantages: adaptive control provides a framework for stability and efficiency, while deep reinforcement learning improves decision-making quality and adaptive ability by continuously learning the behavior of the power grid.

[0193] In some embodiments, the objective function combining adaptive optimal control and deep reinforcement learning may be as follows:

[0194] ;

[0195] where: is the joint optimization objective, representing the objective of optimizing the operation of the power grid considering optimal control and reinforcement learning.

[0196] is the weighting factor, which is used to balance the impacts of adaptive optimal control and deep reinforcement learning. This factor controls the trade-off between control strategy adjustment and deep reinforcement learning adjustment in the system.

[0197] Specifically, the joint optimization method enables the system to improve the effect of the control strategy through reinforcement learning while ensuring stability, so that the power grid can better cope with dynamic changes and emergencies.

[0198] The core of deep reinforcement learning lies in the balance between exploration and exploitation. Exploration refers to trying new and unknown operations, while exploitation is making decisions using known optimal strategies. In the power grid, deep reinforcement learning continuously explores new scheduling strategies, finds the best control strategy, and gradually improves it during actual operation. To enhance the learning efficiency and long-term stability of the system, the Q-value function is updated through the following formula:

[0199] ;

[0200] where: is the learning rate, which represents the update speed of new information to the model and usually controls the influence of new information in each learning process. is the current action is the next state that the power grid reaches after represents the next state all possible actions under is the immediate reward, which reflects the influence of the current power grid strategy on the operating state.

[0201] As an option, deep reinforcement learning can approximate through a neural network , that is, through a convolutional neural network or a fully connected neural network to process the large-scale data and complex state space of the power grid.

[0202] Step S7 provides the power grid with the ability of real-time adjustment by combining adaptive optimal control and deep reinforcement learning, enabling it to respond quickly in the face of dynamic loads and emergencies. Adaptive control ensures the stability and efficiency of the power grid, while deep reinforcement learning enables the power grid to efficiently cope with complex changes by continuously optimizing the scheduling strategy.

[0203] S8. Automatically trigger a hierarchical safety warning response according to the health status of the power grid and the risk assessment results;

[0204] In step S8, the system automatically triggers warning responses at different levels according to the health status assessment and risk assessment results of the power grid. The health status assessment of the power grid is obtained from the Bayesian network model and other prediction models in the previous steps, while the risk assessment combines real-time data and historical data. In order to trigger different warning responses according to the assessment results, the system needs to establish a hierarchical mechanism. The specific formula is as follows:

[0205] ;

[0206] Where: represents the warning level at time . The warning level of the power grid is dynamically set by the system according to the health status and risk assessment results of the power grid, usually divided into different levels such as low, medium, and high; represents the risk assessment result of the power grid at time , usually an evaluation value obtained by comprehensively considering the current health status, potential risks, and historical data of the power grid. This result is obtained by combining real-time data and historical data; represents the information entropy at time , which measures the uncertainty and redundancy of the information on the current health status of the power grid. The higher the entropy, the greater the uncertainty, and a higher-priority warning response may be required.

[0207] This formula helps the system dynamically adjust the warning level according to real-time evaluation results. Higher risk assessment values and higher uncertainty (i.e., higher entropy values) usually trigger higher warning levels, indicating the need for more urgent emergency responses.

[0208] By automatically triggering warning responses, the system can initiate warnings automatically when abnormalities or potential risks occur in the power grid and take corresponding emergency measures. According to the health status and risk assessment of the power grid, the system automatically adjusts the response strategy to ensure that the power grid quickly resumes stability during emergencies. The automated warning response can be expressed as the following optimization formula:

[0209] ;

[0210] Where: represents the control input or scheduling decision at time and determines the warning response measures that the system needs to take. Control inputs include operations such as adjusting the load and enabling backup power supplies; represents the cost of the response measures, which is usually related to factors such as the actual cost of implementing the response strategy and equipment scheduling. The choice of control strategy aims to minimize the cost; is a regulation factor that controls the influence weight of risk assessment and health status on the response strategy. This factor balances the effect of response measures and the actual cost; represents the impact of the risk assessment and health status of the power grid on the stability and security of the power grid after taking the control input . This item reflects the mitigation effect of different warning responses on power grid risks.

[0211] Through this formula, the system can flexibly select the optimal emergency response strategy according to the health status and risk assessment results of the power grid, reducing both the response cost of the system and ensuring the safety and stability of the power grid.

[0212] During the operation of the power grid, the health status and risk assessment of the power grid are closely related, and the assessment of the health status is usually the basis for risk assessment. By real-time monitoring and evaluating the power grid status and operation data, the system can timely identify potential safety hazards and automatically trigger the response mechanism. The formula after combining the power grid health status assessment and risk assessment is usually as follows:

[0213] ;

[0214] Where: is the risk assessment result of the power grid, representing the risk level at time . The risk assessment of the power grid is jointly determined by factors such as the health status of the power grid, load demand, and equipment condition; represents the real-time monitoring data of the power grid status, such as voltage, current, frequency, etc. These data reflect the current health status of the power grid; Represents the historical data of the power grid, which is usually used for trend analysis and prediction to help identify potential risks.

[0215] Specifically, the system utilizes real-time data and historical data to conduct comprehensive analysis and obtain the risk assessment value of the power grid at the current moment . This value is the basis for triggering early warning responses at different levels.

[0216] To further optimize the accuracy and timeliness of the power grid early warning response, the system continuously optimizes the response strategy through deep learning and reinforcement learning methods. The optimization of the early warning response is continuously updated through a feedback mechanism. The goal of the power grid is to minimize the response time while ensuring the stability of the power grid. The response strategy of the power grid is adjusted through the following optimization formula:

[0217] ;

[0218] Where: Represents the goal of the optimized response strategy, and the goal is to minimize costs and improve the operating efficiency of the power grid; Represents the cost when taking response measures ; Is a weighting factor that adjusts the cost of control input and the impact on the health status of the power grid to ensure that the power grid operates in an optimal state.

[0219] Through this optimization formula, the system can adjust the emergency response strategy in real time to ensure that the power grid can recover quickly and remain stable, while optimizing the cost and resource allocation of the response.

[0220] By dynamically adjusting the response strategy, the power grid can quickly take appropriate measures in the face of emergencies and complex environments, thereby ensuring the efficient and safe operation of the power grid. The automated early warning response mechanism not only improves the emergency response speed and accuracy of the power grid, but also optimizes the resource allocation and cost management of the power grid.

[0221] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A hierarchical security early warning method based on intelligent power grid simulation, characterized in that, The method includes the following steps: S1. Collect the operation data of the smart grid, including real-time monitoring data of voltage, current, power factor, and temperature, and process the collected operation data; S2. Optimize the estimation of the grid state using the extended Kalman filter algorithm; S3. Establish a non-linear dynamic model of the smart grid, and predict the health state of the grid according to the dynamic behavior of the grid; S4. Construct a Bayesian network model, evaluate the risk of the grid through probability inference, and judge the health condition of the grid; S5. Based on the Nash equilibrium model in game theory, cooperate to optimize the behaviors of multiple decision-making entities of the grid to make the grid globally stable; The optimization of the behaviors of multiple decision-making entities of the grid based on the Nash equilibrium model in game theory includes: Set multiple control entities of the grid, including load dispatch, generator dispatch, and standby power supply, as participants in the game; Use the Nash equilibrium solution to optimize the decisions of each entity through game theory to achieve the globally optimal grid operation state; Each entity adjusts its decision-making behavior according to the health condition and risk assessment result of the grid to ensure the stable operation of the grid; In the grid, the goal of load dispatch is to minimize load fluctuations and grid operation costs, and the goal of generator dispatch is to dispatch the operation of generators according to the grid load demand to ensure the stability and optimal allocation of power supply; S6. Optimize the setting of warning levels and information flow transmission strategies using the maximum entropy principle in information theory, and adjust the information distribution and transmission methods of each warning level; The maximum entropy principle optimizes the setting of warning levels through the following formula: ； Wherein: represents the time of the early warning level. The early warning level of the power grid is dynamically set based on the risk assessment results and the information entropy value to ensure that the early warning response can target the actual risk state of the power grid; represents the time of the power grid risk assessment result, including the health index of the power grid and the probabilities of various risks; the power grid risk assessment result is the key basis for adjusting the early warning level; represents the time of the information entropy, which measures the redundancy and information volume of the power grid early warning information; S7. Based on adaptive optimal control and deep reinforcement learning, adjust the operation strategy of the grid in real time to optimize the warning response; S8. Automatically trigger hierarchical safety warning responses according to the grid health state and risk assessment results.

2. The hierarchical security warning method based on intelligent power grid simulation according to claim 1, characterized in that, The optimization of the estimation of the grid state using the extended Kalman filter algorithm includes: Based on the extended Kalman filter algorithm, optimize the estimation of the non-linear state of the grid; Update the health state of the grid in real time, use the grid measurement data and dynamic model to correct the prediction of the grid state, and reduce the influence of noise on the system estimation; Adjust the error estimation of the system by calculating the Kalman gain to improve the prediction accuracy of the grid state.

3. A hierarchical security early warning method based on intelligent grid simulation according to claim 1, characterized in that The establishment of the non-linear dynamic model of the smart grid includes: Use the operation data to construct the state vector of the grid, and describe the dynamic relationship between the states of the grid through non-linear functions; Introduce a perturbation term to simulate the influence of external factors on the grid system, so that the grid model can better adapt to different operating environments; Use Lyapunov stability theory to analyze the stability of the grid model to ensure that the model remains stable under various perturbations.

4. A hierarchical security early warning method based on intelligent power grid simulation according to claim 1, characterized in that The construction of the Bayesian network model includes: Construct the Bayesian network of the grid by establishing the conditional dependence relationship between the parameters of the grid; Calculate the conditional probability distribution of each node according to the historical operation data of the grid, and infer its risk probability according to the current grid state; Based on the inference result, evaluate the risk level of the grid in different operating states, and provide decision support for the grid operation through Bayesian inference.

5. A hierarchical security warning method based on intelligent power grid simulation according to claim 1, characterized in that The setting of the warning level and the information flow transmission strategy optimized by using the maximum entropy principle in information theory include: Based on the maximum entropy principle in information theory, by optimizing the information distribution of each warning level in the power grid, the system can quickly transmit risk information; Set corresponding information transmission mechanisms for different warning levels to ensure the effectiveness of the information flow; Under different risk levels, according to the state and real-time data of the power grid, dynamically adjust the information distribution strategy to reduce redundant information.

6. A hierarchical security warning method based on intelligent power grid simulation according to claim 1, characterized in that, The real-time adjustment of the power grid operation strategy based on adaptive optimal control and deep reinforcement learning includes: Introduce a deep reinforcement learning algorithm, use the real-time data of the power grid to train the intelligent decision-making system, and adaptively adjust the control strategy of the power grid; Combine the optimal control theory, and optimize the emergency response mechanism of the power grid by learning the operation mode and risk state of the power grid in real time; Through reinforcement learning training, the system can continuously optimize the warning timing and response intensity, and reduce false alarms and missed alarms.

7. A hierarchical security warning method based on intelligent power grid simulation according to claim 1, characterized in that, The automatic triggering of hierarchical safety warning responses based on the health status of the power grid and the risk assessment results includes: According to the evaluation results of the power grid health status, automatically select the corresponding warning level, and trigger a warning response through the intelligent decision-making system; In high-risk situations, the system can automatically adjust the operation strategy of the power grid, including measures such as enabling standby power supplies and adjusting load distribution; In low-risk situations, the system can select a non-intervention response method to keep the power grid stable.

8. A hierarchical security warning method based on intelligent power grid simulation according to claim 1, characterized in that The further prediction of the power grid risk by the method based on the power grid simulation model includes: Use a dynamic power grid simulation model, combine the historical data and real-time operation data of the power grid, and predict the potential risks of the power grid from multiple angles; Through big data analysis technology, simulate and predict the risk scenarios of different fault modes and equipment failures, and identify in advance the security threats that the power grid may face.

9. A hierarchical security early warning method based on intelligent power grid simulation according to claim 1, characterized in that The feedback mechanism of the power grid health status and risk assessment results includes: Through a real-time monitoring and data feedback system, periodically update the health status of the power grid and the risk assessment results; Based on the feedback mechanism, the system continuously adjusts the warning strategy and response behavior to ensure that the power grid can flexibly respond to emergencies in different operating environments.

Images