Power grid operation safety margin improving method and system

Abstract

The invention discloses a power grid operation safety margin improvement method and system. The method comprises the steps of obtaining power grid data and performing preprocessing; constructing a power grid simulation model based on the preprocessed data to perform power grid fault simulation; identifying key nodes of the power grid based on a power grid fault simulation result; based on the power grid key nodes, constructing a power grid load prediction model and predicting load conditions of the power grid key nodes; obtaining a power grid safety margin through a current load and a load demand value predicted by the load prediction model, and deploying an energy storage regulation and control strategy at a key node in combination with the power grid safety margin; and network security encryption is carried out. According to the invention, the load prediction result is combined with the power grid energy storage system, and under the guidance of the load prediction result, the dynamic distribution and adjustment of power are realized, the change of the power grid load is coped with in time, the optimal configuration of power resources is realized, the power grid pressure during the peak load period is reduced, and the stable operation of the power grid is ensured. And the safety margin and the operation efficiency of the power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of grid operation safety automation processing, and particularly to a method and system for improving the safety margin of grid operation. Background Art

[0002] With the continuous growth of global energy demand, the security and stability of power systems have become one of the core issues in grid operation. As a measure of the ability of the grid to remain in normal operation when suffering from disturbances, the grid safety margin is directly related to the reliability and economy of the grid. With the increasing complexity of modern grid structures, such as the widespread application of distributed energy systems and the enhancement of load volatility, the research on improving the grid operation safety margin has gradually shifted to dynamic simulation and real-time monitoring technologies. By constructing more refined grid models and applying advanced prediction and control algorithms, the response ability of the grid to emergencies is enhanced, and the continuity and security of grid operation are ensured.

[0003] However, there are still many deficiencies in the existing technologies for grid safety margin management. First of all, existing grid fault simulation models often simplify the dynamic characteristics of the grid and are difficult to accurately reflect the actual operating state of the grid under fault conditions, resulting in deviations between the prediction results and the actual situation. In addition, existing grid energy storage system control strategies are mostly based on static optimization and fail to effectively combine real-time prediction data, resulting in limited ability of the grid to respond to emergencies and making it difficult to optimize power quality and reduce operating costs while ensuring the grid safety margin. Finally, with the increase of cyber security threats, grid data faces more and more security risks during transmission and processing. Existing encryption technologies are unable to cope with these complex cyber attacks, further affecting the security and reliability of grid operation. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for improving the safety margin of grid operation to solve the problem that existing grid energy storage system control strategies are mostly based on static optimization and fail to effectively combine real-time prediction data, resulting in limited ability of the grid to respond to emergencies and unable to effectively improve the safety margin of grid operation.

[0006] To solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for improving the safety margin of grid operation, including:

[0008] Obtaining grid data and performing preprocessing;

[0009] Constructing a grid simulation model based on the preprocessed data for grid fault simulation;

[0010] Identify the key nodes of the power grid based on the power grid fault simulation results;

[0011] Based on the identified key nodes of the power grid, construct a power grid load prediction model and predict the load conditions of the key nodes of the power grid;

[0012] Obtain the power grid safety margin through the current load of the power grid and the load demand value predicted by the power grid load prediction model, and deploy energy storage control strategies at the key nodes in combination with the power grid safety margin;

[0013] Perform network security encryption on the power grid data after deployment.

[0014] As a preferred solution of the power grid operation safety margin improvement method described in the present invention, wherein: the construction of the power grid simulation model includes:

[0015] Calculate the power grid simulation and load flow, and construct a power grid simulation model in combination with the preprocessed power grid data;

[0016] Perform preliminary simulation operation, and compare the simulation results with the operation data under similar conditions in the historical operation data of the actual power grid to optimize the model;

[0017] For non-linear components or devices with time-varying characteristics, introduce custom functions.

[0018] As a preferred solution of the power grid operation safety margin improvement method described in the present invention, wherein: the power grid fault simulation includes: setting a short-circuit fault;

[0019] The short-circuit fault simulation includes obtaining the nodes with high load and in the key transmission lines in the power grid, setting short-circuit faults for the selected nodes in the power grid simulation model, running the power grid simulation model, and calculating the short-circuit current according to Ohm's law:

[0020] Obtain the maximum short-circuit current of all nodes and record the power grid node with the largest short-circuit current value.

[0021] As a preferred solution of the power grid operation safety margin improvement method described in the present invention, wherein: the power grid fault simulation includes: setting an open-circuit fault;

[0022] The open-circuit fault simulation includes removing each transmission line in the power grid from the power grid model one by one for fault simulation;

[0023] Record the voltage amplitude of each node in the power grid under normal and open-circuit fault conditions respectively and ;

[0024] Calculate the voltage magnitude difference of each node under normal and open - circuit fault conditions ;

[0025] Compare the voltage magnitude distribution diagrams of all nodes in the power grid under normal and open - circuit fault conditions;

[0026] Set the voltage magnitude difference reference value within the first threshold range by combining the voltage magnitude differences under normal conditions; The first threshold range;

[0027] Based on the first threshold range, determine the risk type of the node and mark the abnormal nodes in the voltage magnitude distribution diagram.

[0028] As a preferred solution of the method for improving the power grid operation safety margin of the present invention, wherein: the power grid fault simulation includes: setting an overload fault;

[0029] The overload fault simulation includes selecting a power grid node operating within a preset rated capacity range, increasing the load of this node in the power grid simulation model, simulating the overload scenario and running the power grid simulation model, and calculating the voltage of this node;

[0030] Calculate the voltage drop value between the node voltage under overload fault conditions and the voltage under normal conditions;

[0031] Set a voltage drop threshold, compare it with the voltage drop value. If the voltage drop value is greater than the voltage drop threshold, it is determined that the node voltage drops significantly, and record the nodes whose voltages exceed the set threshold and drop.

[0032] As a preferred solution of the method for improving the power grid operation safety margin of the present invention, wherein: based on the power grid fault simulation results, identifying the key nodes of the power grid includes:

[0033] Based on the short - circuit fault, open - circuit fault and overload fault processes, monitor and record the voltage, current and power changes of each node in the power grid during each fault simulation;

[0034] Combined with the analysis results of short - circuit faults, open - circuit faults and overload faults, identify the key nodes of the power grid, including the nodes with the largest short - circuit current value in the short - circuit simulation, the abnormal nodes after the transmission line is disconnected, and the nodes whose voltages exceed the set threshold and drop during the overload fault.

[0035] As a preferred solution of the method for improving the power grid operation safety margin of the present invention, wherein: obtain the power grid safety margin through the current load of the power grid and the load demand value predicted by the power grid load prediction model, and deploy an energy storage regulation strategy at the key nodes in combination with the power grid safety margin, including:

[0036] Based on the current load of the power grid The grid load forecasting model predicts that the grid is in time Load demand value at , calculation is at time The grid security margin , expressed as:

[0037]

[0038] in, From the present time to the future time Any time in between;

[0039] like <1, then the charging operation is performed and the charging capacity is calculated ;

[0040] Calculate the power difference M between the real-time power generation and the load demand, expressed as:

[0041]

[0042] in, It's time The power generation of the energy storage system at the time

[0043] The power difference Convert to current , expressed as:

[0044]

[0045] in, Is the grid in time The voltage at

[0046] Calculate the charge capacity based on the current MI , expressed as:

[0047]

[0048] in, is in The grid security margin at It's time The remaining capacity of the energy storage system is is the maximum capacity of the energy storage system;

[0049] like >1, then the discharge operation is performed and the discharge capacity is calculated , expressed as:

[0050]

[0051] like =1, no operation is performed.

[0052] In a second aspect, the present invention provides a system for enhancing the safety margin of power grid operation, including:

[0053] An acquisition module, configured to acquire power grid data and perform preprocessing;

[0054] A simulation module, configured to construct a power grid simulation model based on the preprocessed data to perform power grid fault simulation;

[0055] An identification module, configured to identify key nodes of the power grid based on the power grid fault simulation results;

[0056] A prediction module, configured to construct a power grid load prediction model and predict the load conditions of key nodes of the power grid based on the identified key nodes of the power grid;

[0057] A deployment module, configured to obtain the safety margin of the power grid through the current load of the power grid and the predicted load demand value predicted by the power grid load prediction model, and deploy an energy storage regulation strategy at key nodes in combination with the safety margin of the power grid;

[0058] An encryption module, configured to perform network security encryption on the deployed power grid data.

[0059] In a third aspect, the present invention provides an electronic device, including:

[0060] A memory and a processor;

[0061] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method for enhancing the safety margin of power grid operation are implemented.

[0062] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of the method for enhancing the safety margin of power grid operation are implemented.

[0063] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining the load prediction results with the power grid energy storage system, the load prediction model can help arrange power generation and distribution resources more accurately, reduce operating costs, improve efficiency at the same time, and respond to changes in power grid load in a timely manner; Calculate the safety margin of the power grid by combining the current load with the predicted demand, and adjust the energy storage strategy when necessary to enhance the stability of the power grid, intelligently control the power grid, and realize the dynamic distribution and adjustment of electricity under the guidance of the load prediction results, achieving the optimal allocation of power resources, reducing the power grid pressure during peak load periods, ensuring the stable operation of the power grid, and improving the safety margin and operation efficiency of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0065] Figure 1 It is a schematic diagram of the overall process of the method for improving the safety margin of power grid operation according to an embodiment of the present invention;

[0066] Figure 2 It is a schematic diagram of the process of key nodes for power grid fault simulation and identification in the method for improving the safety margin of power grid operation according to an embodiment of the present invention. Detailed Embodiments

[0067] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will provide a detailed description of the specific embodiments of the present invention with reference to the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0068] Embodiment 1

[0069] Referring to Figure 1 , as an embodiment of the present invention, a method for improving the safety margin of power grid operation is provided, including:

[0070] S100: Obtain power grid data and perform preprocessing;

[0071] S200: Build a power grid simulation model based on the preprocessed data to perform power grid fault simulation;

[0072] S300: Identify the key nodes of the power grid based on the power grid fault simulation results;

[0073] S400: Build a power grid load prediction model based on the identified key nodes of the power grid and predict the load conditions of the key nodes of the power grid;

[0074] S500: Obtain the power grid safety margin through the current load of the power grid and the load demand value predicted by the power grid load prediction model, and deploy an energy storage regulation strategy at the key nodes in combination with the power grid safety margin;

[0075] S600: Perform network security encryption on the deployed power grid data.

[0076] It should be noted that the effectiveness and accuracy of the current power grid simulation model construction and fault simulation recognition algorithms directly affect the subsequent steps, such as the deployment of energy storage control strategies; the power grid structure and operating conditions are constantly changing, and static critical node identification may not be able to adapt to this change. With the change of the power grid load pattern, the effectiveness of model update is insufficient; as a result, the safety margin prediction and update are not timely, affecting the data transmission efficiency.

[0077] Therefore, in view of the above existing problems, through the machine learning model in steps S100 - S600, the simulation preview of fault scenarios is carried out, different fault scenarios are set for different faults, and the load prediction is combined with critical nodes to obtain the required safety margin, and the energy storage strategy is adjusted when necessary to enhance the power grid stability, realizing timely calculation update and encryption.

[0078] Embodiment 2

[0079] Referring to Figure 1 - Figure 2 , as an embodiment of the present invention, based on the above embodiment, a method for improving the safety margin of power grid operation is provided.

[0080] In the embodiment of the present application, the steps of obtaining power grid data and preprocessing in step S100 include the following steps:

[0081] S101: Install the SCADA system at the power grid generator nodes, load nodes, substation nodes, power collection nodes, transmission line endpoints and power grid boundary nodes, and use the SCADA system to collect the power grid data of each node in real time, including power grid topology data, historical operation data and equipment parameters;

[0082] Specifically, the power grid topology data may include: the topology structure of the power grid, including substations, transmission lines, distribution network nodes and their connection relationships;

[0083] Specifically, the historical operation data may include: the historical fault data of the power grid lines and the load data of each node;

[0084] Specifically, the equipment parameters may include: the equipment parameters of each node and the resistance of the transmission line;

[0085] S102: Perform data cleaning and data verification on the collected power grid data.

[0086] It should be noted that by collecting real-time data during power grid operation, the status information of each key node of the power grid can be comprehensively obtained, such as voltage, current, power, frequency, etc., providing a basis for subsequent power grid operation analysis and simulation; preprocessing the data, performing data cleaning, removing outliers and noise in the data, and ensuring the accuracy and consistency of the data. Through normalization processing, data with different dimensions can be compared and analyzed under the same standard, thereby avoiding errors caused by dimension differences. In addition, reasonable interpolation and correction are performed for missing values to ensure the integrity and continuity of the data and reduce the risk of error transmission.

[0087] In an alternative embodiment, the power grid data obtained in step S100 may further include meteorological data, and the meteorological data includes humidity, temperature, rainfall, etc. The preprocessing may further include feature engineering, for example: encoding different types of variables and converting categorical variables into numerical types so that they can be correctly interpreted by machine learning algorithms.

[0088] In another alternative embodiment, the power grid data obtained in step S100 may further include user behavior data, and the preprocessing may further include principal component analysis (PCA) or other dimensionality reduction techniques to remove redundant features and improve the performance of subsequent models.

[0089] In the embodiment of the present application, building a power grid simulation model in step S200 includes the following steps S201 - S203:

[0090] S201: Calculate the power grid simulation and load flow, and build a power grid simulation model in combination with the preprocessed power grid data;

[0091] Specifically, it is preferably to calculate the power grid simulation and load flow through MATPOWE.

[0092] S202: Conduct a preliminary simulation run, compare the simulation results with the operation data under similar conditions in the historical operation data of the actual power grid to optimize the model;

[0093] The optimized model refers to calculating the error calculation gradient of the simulation results and the operation data under similar conditions in the historical operation data of the actual power grid, iterating the parameters of the power grid simulation model using the gradient descent method according to the calculated gradient, and setting the mean square error as the loss function. When the loss function converges, the iterative optimization is completed.

[0094] S203: For nonlinear components or devices with time-varying characteristics, introduce custom functions.

[0095] In an alternative embodiment, the power grid simulation model in step S200 is constructed through detailed electromagnetic transient simulation (EMT) based on physics, which can accurately simulate the transient behavior of the power system, including non-linear elements and fast-changing processes; it is more suitable for modern power grids with a large amount of renewable energy access, energy storage systems or other complex power electronic devices.

[0096] In another alternative embodiment, the power grid simulation model in step S200 can also be simulated through a random forest model or the like.

[0097] It should be additionally noted that for non-linear elements or devices with time-varying characteristics, functions such as the diode non-linear characteristic function and the time-delay dependent Lyapunov functional can be introduced. Specifically:

[0098] The diode non-linear characteristic function is used for non-linear elements and is specifically:

[0099]

[0100] where is the reverse saturation current, is the thermal voltage, n is the ideality factor, and V and I are the voltage and current of the non-linear element respectively;

[0101] The time-delay dependent Lyapunov functional is used for devices with time-varying characteristics and is specifically:

[0102]

[0103] where is the device voltage at time t, is the time-delay history of the system state, T is the transpose operation, s is the integration variable, is the time-delay duration, and P and Q are positive definite matrices.

[0104] It should be noted that in this application, MATPOWE is preferably used to calculate the power grid simulation and load flow, which is suitable for steady-state analysis and long-term planning research; by comparing the simulation results with the historical operation data of the actual power grid, the deviations in the model can be quickly identified and adjusted, reducing the demand for a large amount of computing resources and improving the accuracy of the simulation. Introducing custom functions to handle non-linear elements or time-varying characteristic devices can enable customized modeling for specific problems without relying on complex physical models or a large amount of training data. Compared with using EMT or other deep learning models, methods such as MATPOWE can achieve good performance through existing theoretical knowledge and a small amount of calibration, reducing the dependence on large-scale historical data; the cost is lower, and it can also meet the steady-state analysis needs of most power systems.

[0105] In the embodiments of the present application, as Figure 2 , in step S200, power grid fault simulation is performed, including: setting a short-circuit fault, specifically including the following steps A1 - A2:

[0106] A1: The short-circuit fault simulation includes obtaining the nodes with high load and in the critical transmission lines in the power grid. In the power grid simulation model, set a short-circuit fault for the selected nodes, run the power grid simulation model, and calculate the short-circuit current according to Ohm's law:

[0107] Exemplarily, it can be expressed as:

[0108]

[0109] Wherein, is the short-circuit current, is the voltage of the short-circuit node, is the equivalent impedance during the fault;

[0110] A2: Obtain the maximum short-circuit current of all nodes and record the power grid node with the maximum short-circuit current value.

[0111] In the embodiments of the present application, as Figure 2 , in step S200, power grid fault simulation is further performed, including: setting an open-circuit fault, specifically including the following steps B1 - B6:

[0112] B1: For each transmission line in the power grid, remove it from the power grid model one by one for fault simulation;

[0113] B2: Record the voltage amplitudes and of each node in the power grid under normal and open-circuit fault conditions respectively;

[0114] B3: Calculate the voltage amplitude difference of each node under normal and open-circuit fault conditions;

[0115]

[0116] B4: Compare the voltage amplitude distribution diagrams of all nodes in the power grid under normal and open-circuit fault conditions;

[0117] Specifically, software such as MATLAB can be used to draw the distribution diagrams.

[0118] B5: Combine the voltage amplitude differences under normal conditions to set the first threshold range of the reference value of the voltage amplitude difference ;

[0119] Exemplarily, based on historical experience and industry specifications, set the reference value of the voltage amplitude difference ∆Vi as ±5% of the voltage amplitude difference under normal conditions;

[0120] If ∆Vi is less than 95% of the voltage amplitude difference under normal conditions, it is determined that there is a low voltage risk at this node, which may lead to a decline in power supply quality or equipment failure to operate, and reactive power compensation is adjusted and voltage support is increased;

[0121] If ∆Vi is greater than 105% of the voltage amplitude difference under normal conditions, it is determined that there is a high voltage risk at this node, which may damage electrical equipment and cause power grid protection actions to operate, and the reactive power injection at this node is reduced;

[0122] B6: Determine the risk type existing at the node based on the first threshold range, and mark the abnormal nodes in the voltage amplitude distribution map.

[0123] In the embodiment of the present application, as Figure 2 , when simulating grid faults in step S200, it further includes: setting an overload fault, specifically including the following steps C1 - C3:

[0124] C1: The overload fault simulation includes selecting a grid node operating within the preset rated capacity range, increasing the load of this node in the grid simulation model, simulating the overload scenario and running the grid simulation model, and calculating the voltage of this node;

[0125] Specifically, it can be expressed as:

[0126]

[0127] Among them, is the overload current, is the line impedance;

[0128] C2: Calculate the node voltage under the overload fault condition and the voltage drop value ∆V between the voltage under normal conditions;

[0129] C3: Set the voltage drop threshold ∆Vl, compare it with the voltage drop value, if the voltage drop value is greater than the voltage drop threshold, it is determined that the node voltage has a significant drop, and record the nodes where the voltage drops beyond the set threshold.

[0130] In an alternative embodiment, when simulating grid faults, it may further include circuit breaker tripping or generator faults;

[0131] In another alternative embodiment, when simulating grid faults, it may further include ground faults or voltage instability conditions.

[0132] It should be noted that through power grid fault simulation, the system can identify the vulnerability and potential faults of the power grid, especially early warning of potential hazards that may cause large-scale power outages or serious system instability, which helps to optimize the emergency plan of the power grid, provide reliable data support, enable power companies to formulate corresponding risk response strategies before faults occur, thus greatly reducing the possibility of large-scale power outages or system collapses caused by sudden faults, enhancing the flexibility of the power grid to respond to fault scenarios, providing a scientific basis for the long-term operation safety of the power grid, and through systematic fault simulation, the reliability and security of power grid operation are significantly improved, ensuring that under various possible fault conditions, it can quickly resume the normal operation state, reduce the impact of power supply interruption on society and economy, and further improve the safety margin of power grid operation.

[0133] In the embodiment of the present application, based on the power grid fault simulation results in step S300, identifying the key nodes of the power grid includes:

[0134] Based on the short-circuit fault, open-circuit fault, and overload fault processes, monitor and record the voltage, current, and power changes of each node in the power grid during each fault simulation.

[0135] Combined with the analysis results of short-circuit faults, open-circuit faults, and overload faults, identify the key nodes of the power grid, including the node with the largest short-circuit current value in the short-circuit simulation, the abnormal node after the transmission line is disconnected, and the node where the voltage drops below the set threshold during the overload fault.

[0136] In an alternative embodiment, based on the power grid fault simulation results in step S300, the key nodes of the power grid can also be identified through complex network theory for the topological structure of the power system. The power grid is regarded as a graph composed of nodes (such as power plants, substations) and edges (transmission lines). Then, apply centrality metrics (such as degree centrality, betweenness centrality, and closeness centrality) to evaluate the importance of each node in the network.

[0137] In another alternative embodiment, based on the power grid fault simulation results in step S300, the key nodes of the power grid can also be identified through risk assessment and vulnerability analysis. Combine the methods of probability theory and statistics to conduct risk assessment on each component in the power grid, considering the possibility of its failure and its impact on the entire system.

[0138] It should be noted that identifying key nodes in step S300 can discover which nodes exhibit high risk in various fault scenarios and have a significant impact on system stability. This allows for targeted strengthening of the monitoring and maintenance of these nodes, early deployment of preventive measures, and avoidance of systemic risks caused by key node failures. At the same time, the identified key nodes also provide key data support for subsequent power grid load forecasting and intelligent control strategies, ensuring the safe operation of these nodes during peak load periods and abnormal situations, improving the overall operational safety of the power grid, and providing a basis for further optimization and intelligent control.

[0139] In the embodiment of the present application, in step S400, based on the identified key nodes of the power grid, a power grid load forecasting model is constructed and the load conditions of the key nodes of the power grid are predicted, including the following steps S401 - S403:

[0140] S401: Construct a power grid load forecasting model through a long short-term memory network (LSTM), including an input layer, a hidden layer, and an output layer, and set the input layer as power grid data;

[0141] S402: Use historical power grid data as a training set, input it into the power grid load forecasting model for training, and use the mean squared error and the Adam optimizer as loss functions to optimize the power grid load forecasting model;

[0142] S403: Set a time period to loop and update the power grid load forecasting model, input the real-time collected power grid data into the power grid load forecasting model, and obtain the predicted value of the power grid load demand.

[0143] Specifically, the predicted value of the power grid load demand may include the power generation power of the energy storage system, the remaining capacity of the energy storage system, and the voltage.

[0144] In an alternative embodiment, the power grid load forecasting model in step S400 can also be constructed through a hybrid model of a convolutional neural network and a recurrent neural network.

[0145] In another alternative embodiment, the power grid load forecasting model in step S400 can also be constructed through a support vector regression model (SVR).

[0146] It should be noted that by constructing a power grid load prediction model and combining real-time data with simulation results, the prediction model can be dynamically adjusted, enhancing its response ability to sudden load changes. This can provide a basis for the subsequent regulation strategy of the power grid energy storage system, help optimize the charge and discharge plan of the energy storage system, and thus maximize the economy and efficiency of power grid operation. In addition, the load prediction model can also provide early warnings for power grid operation management, identify possible load overload situations in advance, reduce the risk of power supply interruption, better plan power resources, and avoid equipment overload and system instability caused by sudden load surges.

[0147] In the embodiment of the present application, in step S500, based on the current load of the power grid and the load demand value predicted by the power grid load prediction model, the power grid safety margin is obtained, and an energy storage regulation strategy is deployed at key nodes in combination with the power grid safety margin, including:

[0148] Based on the current load of the power grid and the load demand value of the power grid at time predicted by the power grid load prediction model , calculate the power grid safety margin at time , which is expressed as:

[0149]

[0150] wherein, is any time between the current time and the future time ;

[0151] If <1, perform a charging operation and calculate the charging amount ;

[0152] Calculate the power difference M between the real-time power generation power and the load demand, which is expressed as:

[0153]

[0154] wherein, is the power generation power of the energy storage system at time ;

[0155] Convert the power difference to current , which is expressed as:

[0156]

[0157] wherein, is the voltage of the power grid at time ;

[0158] ​Calculate the charge amount based on the current MI , which is expressed as:

[0159]

[0160] Among them, is the grid safety margin at , is the remaining capacity of the energy storage system at time , is the maximum capacity of the energy storage system;

[0161] It should be noted that is the integral of the short-term safety margin of the grid from the initial time to time t. Considering the dynamic change of the grid safety margin over time, to help the charging strategy better respond to the long-term trend of the grid, the margin at a single moment cannot fully reflect the overall stability of the grid over a period of time. Using the integral form can capture the overall change of the grid safety margin, rather than just the instantaneous state at a certain moment. When using the linear method to handle the grid safety margin, it may not be able to fully reflect its impact on the load of the energy storage system, especially in the case of drastic margin changes. By squaring the operation (1 + )2, introducing non-linear characteristics, it can be more sensitive to the change of the grid safety margin, ensuring that when the grid safety margin is low, the charging process can slow down quickly to maintain the overall stability of the grid;

[0162] Among them, it should also be noted that:

[0163]

[0164] The grid is prone to danger when approaching the full charge state. It is necessary to avoid safety problems caused by overcharging through precise control strategies. The linear method cannot work efficiently throughout the entire charging process of the battery. Therefore, a non-linear formula is introduced for power adjustment to provide a smooth charging curve, ensuring that the charging rate automatically decreases in a dangerous state to prevent the battery from overheating or being damaged. By non-linearly adjusting the charging rate, the charging efficiency is maximized at different charging stages; fast charging at low battery levels; gradually slowing down the charging rate at high battery levels;

[0165] If > 1, then perform the discharge operation and calculate the discharge amount , which is expressed as:

[0166]

[0167] If = 1, then no operation is performed.

[0168] It should be noted that the logarithmic function , in the interval close to 0, the logarithmic function changes rapidly. When is relatively small, the change will be more significant, and the logarithmic function has a smooth asymptotic characteristic, which can prevent instability during the discharge control process. When there is a large change in the margin, it can also maintain the stability of the system response;

[0169] According to the calculated discharge amount, perform discharge operations to reduce the load demand of the power grid. Based on the safety margin calculation formula, by reducing the load demand of the power grid, improve the operating safety margin of the power grid.

[0170] By predicting future power grid generation data and energy storage status, and deploying an intelligent energy storage system to regulate the power grid, the system can make a rapid response when the power demand fluctuates, ensuring the stability of power supply. Traditional power regulation methods often rely on fixed rules and preset thresholds, making it difficult to cope with rapidly changing load demands. By combining the load prediction results, the energy storage system can dynamically adjust the storage and release of power under the guidance of load prediction. The above steps can not only improve the response speed to sudden load changes, but also reduce the operating pressure of the power grid. Especially during peak load periods, the energy storage system can effectively cut peaks and fill valleys, balance power demand, and avoid the impact on the system caused by power overload. In addition, through intelligent regulation, the power grid can achieve optimal allocation of power resources, ensuring the reasonable distribution of power at each time period and node. The energy storage system can charge during low power demand periods and release power during peak periods, reducing energy waste; at the same time, the reasonable operation of the energy storage system can also reduce the demand for emergency power generation, thereby reducing the overall operating cost; finally, combining load prediction with the intelligent regulation of the energy storage system can significantly improve the safety and stability of operation, thus avoiding power supply interruptions caused by load imbalance.

[0171] In the embodiment of the present application, in step S600, network security encryption is performed on the deployed power grid data, including the following steps:

[0172] Use the symmetric encryption algorithm AES to encrypt the power grid operation data, transmit the data through the TLS data encryption channel, configure digital certificates and public-private key pairs for power grid devices. When devices communicate, use a two-way authentication mechanism to verify the device identity, and deploy an intrusion detection system in the power grid to monitor network processes in real time;

[0173] Regularly perform off-site encrypted backups of the power grid operation data and system configuration.

[0174] In an alternative embodiment, network security encryption of the deployed grid data in step S600 can also be achieved by using a hash function (such as SHA-256 or SHA-3) to generate a digest for the transmitted data and combining asymmetric encryption technology to add a digital signature to the data; the receiving end can ensure the authenticity and integrity of the data source by verifying the signature.

[0175] In another alternative embodiment, network security encryption of the deployed grid data in step S600 can also be achieved by the zero-trust architecture, which assumes that there are potential threats both inside and outside the network and performs strict authentication and authorization control for each access request.

[0176] It should be noted that by performing network security encryption on grid data, it is possible to effectively prevent data leakage or tampering during transmission, thereby ensuring the confidentiality, integrity, and availability of grid operation. For example, load prediction results, energy storage system control strategies, etc., can be safely transmitted between various system components, avoiding security issues caused by data leakage or malicious tampering.

[0177] Embodiment 3

[0178] The above is a schematic solution of a method for improving the security margin of grid operation in this embodiment. It should be noted that the technical solution of the system for improving the security margin of grid operation belongs to the same concept as the technical solution of the above method for improving the security margin of grid operation. For the details not described in detail in the technical solution of the system for improving the security margin of grid operation in this embodiment, reference can be made to the description of the technical solution of the above method for improving the security margin of grid operation.

[0179] This embodiment also provides a system for a method of improving the security margin of grid operation, including:

[0180] An acquisition module, configured to acquire grid data and perform preprocessing;

[0181] A simulation module, configured to construct a grid simulation model based on the preprocessed data to perform grid fault simulation;

[0182] An identification module, configured to identify key grid nodes based on the grid fault simulation results;

[0183] A prediction module, configured to construct a grid load prediction model based on the identified key grid nodes and predict the load conditions of the key grid nodes;

[0184] A deployment module, configured to obtain the grid security margin through the current grid load and the load demand value predicted by the grid load prediction model, and deploy energy storage control strategies at key nodes in combination with the grid security margin;

[0185] An encryption module for network security encryption of the power grid data after deployment.

[0186] This embodiment also provides an electronic device applicable to the situation of improving the safety margin of power grid operation, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the method for improving the safety margin of power grid operation as proposed in the above embodiment.

[0187] This embodiment also provides a storage medium with a computer program stored thereon, and when the program is executed by a processor, it implements the method for improving the safety margin of power grid operation as proposed in the above embodiment.

[0188] The storage medium proposed in this embodiment and the method for improving the safety margin of power grid operation proposed in the above embodiment belong to the same inventive concept. Technical details not described in detail in this embodiment can be referred to in the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0189] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware, and of course, it can also be implemented by hardware. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments of the present invention.

[0190] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A method for improving the safety margin of power grid operation, characterized in that: include: Acquire power grid data and pre-process it; Building a power grid simulation model based on the preprocessed data to simulate power grid faults; Based on the power grid fault simulation results, identify the key nodes of the power grid; Based on the identified key grid nodes, a grid load prediction model is constructed to predict the load conditions of the key grid nodes; The grid safety margin is obtained through the current grid load and the load demand value predicted by the grid load prediction model. The energy storage control strategy is deployed at key nodes based on the grid safety margin. Perform cybersecurity encryption on grid data after deployment; The power grid data includes power grid topology data, historical operation data and equipment parameters; The power grid simulation model is established through detailed physics-based electromagnetic transient simulation (EMT).

2. The method for improving the safety margin of power grid operation according to claim 1, characterized in that: The constructing of the power grid simulation model comprises: Calculate power grid simulation and load flow, and build a power grid simulation model by combining preprocessed power grid data; Conduct preliminary simulation runs and compare the simulation results with historical operating data of the actual power grid under similar conditions to optimize the model; For nonlinear elements or devices with time-varying characteristics, user-defined functions are introduced.

3. The method for improving the safety margin of power grid operation according to claim 1 or 2, characterized in that: The power grid fault simulation includes: setting a short circuit fault; The short-circuit fault simulation includes obtaining nodes with high loads and located in key transmission lines in the power grid, setting short-circuit faults for the selected nodes in the power grid simulation model, running the power grid simulation model, and calculating the short-circuit current according to Ohm's law: Get the maximum short-circuit current of all nodes and record the grid node with the largest short-circuit current value.

4. The method for improving the safety margin of power grid operation according to claim 3, characterized in that: The power grid fault simulation includes: setting a disconnection fault; The line-break fault simulation includes, for each transmission line in the power grid, removing it from the power grid model one by one and performing fault simulation; Record the voltage amplitude of each node of the power grid under normal and line-break fault conditions respectively and ; Calculate the voltage amplitude difference at each node under normal and line-break fault conditions ; Compare the voltage amplitude distribution diagrams of all nodes under normal and line-break fault conditions in the power grid; Set the voltage amplitude difference based on the voltage amplitude difference under normal conditions a first threshold range of a reference value; The risk type of the node is determined based on the first threshold range, and the abnormal node is marked in the voltage amplitude distribution diagram.

5. The method for improving the safety margin of power grid operation according to claim 4, characterized in that: The power grid fault simulation includes: setting an overload fault; The overload fault simulation includes selecting a grid node operating within a preset rated capacity range, increasing the load of the node in a grid simulation model, simulating an overload scenario and running the grid simulation model, and calculating the voltage of the node; Calculate the voltage drop between the node voltage under overload fault condition and the voltage under normal condition; A voltage drop threshold is set and compared with the voltage drop value. If the voltage drop value is greater than the voltage drop threshold, it is determined that the node voltage has dropped significantly, and the node whose voltage has dropped beyond the set threshold is recorded.

6. The method for improving the safety margin of power grid operation according to claim 5, characterized in that: The identifying of key nodes of the power grid based on the power grid fault simulation result includes: Based on the short circuit fault, line break fault and overload fault process, monitor and record the voltage, current and power changes of each node in the power grid in each fault simulation; Combining the analysis results of short-circuit faults, line break faults and overload faults, key nodes of the power grid are identified, including nodes with the largest short-circuit current values ​​in short-circuit simulations, abnormal nodes after transmission line breakage, and nodes where the voltage drops beyond the set threshold in overload faults.

7. The method for improving the safety margin of power grid operation according to claim 6, characterized in that: The grid safety margin is obtained through the current grid load and the load demand value predicted by the grid load prediction model. Energy storage control strategies are deployed at key nodes based on the grid safety margin, including: Based on the current load of the power grid The grid load forecasting model predicts that the grid is in time Load demand value at , calculated at time The grid security margin , expressed as: ,in, From the present time to the future time Any time in between; like <1, then the charging operation is performed and the charging capacity is calculated ; Calculate the power difference M between the real-time power generation and the load demand, expressed as: ,in, It's time The power generation of the energy storage system at the time The power difference Convert to current , expressed as: ,in, Is the grid in time The voltage at Calculate the charge capacity based on the current MI , expressed as: ,in, is in The grid security margin at It's time The remaining capacity of the energy storage system is is the maximum capacity of the energy storage system; like >1, then the discharge operation is performed and the discharge capacity is calculated , expressed as: ,like =1, no operation is performed.

8. A system applied to the method for improving the safety margin of power grid operation according to any one of claims 1 to 7, characterized in that: include: An acquisition module is used to acquire power grid data and perform preprocessing; A simulation module, used to construct a power grid simulation model based on the preprocessed data to simulate power grid faults; An identification module, used for identifying key nodes of a power grid based on power grid fault simulation results; A prediction module is used to construct a power grid load prediction model and predict the load conditions of the key power grid nodes based on the identified key power grid nodes; A deployment module is used to obtain the grid safety margin through the current grid load and the load demand value predicted by the grid load prediction model, and deploy energy storage control strategies at key nodes based on the grid safety margin; The encryption module is used to perform network security encryption on the power grid data after deployment.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, characterized in that: when the computer-executable instructions are executed by the processor, the steps of the method for improving the safety margin of power grid operation as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the steps of the method for improving the safety margin of power grid operation as described in any one of claims 1 to 7 are implemented.

Images