A Low-Temperature Power Grid Operation Optimization Method and Safety Monitoring System Based on Intelligent Algorithms

Abstract

This invention relates to the field of power grid operation optimization technology, and particularly to a method and safety monitoring system for optimizing the operation of a cryogenic power grid based on intelligent algorithms. The method includes the following steps: acquiring cryogenic power grid structure data; dividing the cryogenic power grid structure data into power grid component modules to generate power grid component module data; collecting power grid operation data based on the power grid component module data to obtain standard cryogenic power grid operation data; performing three-dimensional modeling of the power grid operation based on the standard cryogenic power grid operation data to generate cryogenic power grid operation three-dimensional modeling data; and filtering abnormal modules in the cryogenic power grid operation three-dimensional modeling data based on preset abnormal indicator thresholds to obtain cryogenic power grid operation abnormal modules. This invention improves the safety and intelligence of cryogenic power grid operation through intelligent modular analysis, fault propagation prediction and optimization, and a real-time feedback mechanism.

Description

Technical Field

[0001] This invention relates to the field of power grid operation optimization technology, and in particular to a method for optimizing low-temperature power grid operation and a safety monitoring system based on intelligent algorithms. Background Technology

[0002] Early methods for optimizing low-temperature power grids relied primarily on traditional engineering techniques and empirical rules, which often lacked flexibility and adaptability. With the development of computer technology and data analysis capabilities, especially the rise of big data and artificial intelligence (AI) technologies, intelligent algorithms have gradually become core tools for power grid optimization. Power grid optimization methods based on intelligent algorithms, through real-time data acquisition and processing, can accurately predict load changes, equipment operating status, and potential fault risks in the power grid at low temperatures. In recent years, intelligent algorithms such as deep learning, genetic algorithms, and particle swarm optimization (PSO) have been widely applied in power grid operation optimization. For example, deep learning can train models using historical data to achieve accurate prediction and dynamic scheduling of power grid load; particle swarm optimization can be used to optimize the operating strategies of various nodes in the power grid, thereby improving the overall efficiency of the power grid. The combination of intelligent algorithms makes low-temperature power grid optimization methods more efficient, intelligent, and possesses good adaptability and real-time performance. However, current traditional power grid fault detection often struggles to handle sudden faults and complex fault propagation processes caused by low temperatures, and lacks intelligent optimization in emergency handling of power grid operation faults, resulting in lower safety and intelligence in power grid operation. Summary of the Invention

[0003] Therefore, it is necessary to provide a method for optimizing the operation of a cryogenic power grid and a safety monitoring system based on intelligent algorithms to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, a method for optimizing the operation of a cryogenic power grid based on intelligent algorithms is provided, the method comprising the following steps:

[0005] Step S1: Obtain low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate low-temperature power grid operation three-dimensional modeling data.

[0006] Step S2: Based on preset abnormal index thresholds, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation; the abnormal modules of the low-temperature power grid operation are subjected to hierarchical abnormal operation impact analysis to generate the abnormal operation impact factors of the low-temperature power grid operation; the abnormal operation impact factors of the low-temperature power grid operation are used to perform cascade fault propagation analysis on the abnormal modules of the low-temperature power grid operation to generate cascade power fault propagation data of the power grid.

[0007] Step S3: Perform power fault risk prediction on the cascaded power fault propagation data of the power grid to generate power grid power fault risk prediction data; perform cascade operation optimization on the cascaded power fault propagation data of the power grid based on the power grid power fault risk prediction data to generate power grid cascade operation optimization data; construct a power grid operation optimization scheme based on the power grid cascade operation optimization data to generate a power grid cascaded fault operation optimization scheme.

[0008] Step S4: Based on the power grid cascade fault operation optimization scheme, conduct an operation optimization performance evaluation and generate power grid operation optimization performance evaluation data; use the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

[0009] This invention, through modular partitioning and 3D modeling of low-temperature power grid structure data, provides a comprehensive and detailed understanding of the power grid's composition, operating status, and structural characteristics. This provides accurate foundational data for subsequent data acquisition, fault analysis, and optimization, ensuring a true reflection of the power grid's operating status and facilitating further optimization efforts. Anomaly filtering modules based on preset anomaly index thresholds can accurately identify potential fault sources in low-temperature power grid operation. Through hierarchical analysis and cascaded fault propagation, it can reveal fault propagation paths and impact ranges, predicting potential risk areas in the power grid in advance, thus providing precise basis for subsequent fault prediction and optimization, and preventing large-scale power outages. Power fault risk prediction can identify high-risk areas faced by the power grid under low-temperature conditions in advance and make dynamic adjustments. Through cascaded operation optimization, it can effectively avoid or reduce fault propagation, improve the power grid's fault tolerance and stability, ensure stable operation of the power grid in complex environments, and avoid large-scale power outages. Performance evaluation of optimization schemes can quantify the effectiveness of optimization schemes, ensuring the feasibility and effectiveness of operational optimization. By utilizing optimized feedback data to update the system, it is possible to dynamically adapt to changes in the actual operation of the power grid, ensuring that the power grid maintains its optimal operating state in low-temperature environments and improving the system's flexibility and ability to respond to emergencies. Therefore, this invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault propagation prediction and optimization, and a real-time feedback mechanism.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain cryogenic power grid structure data;

[0012] Step S12: Perform grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; divide the low-temperature grid structure data into grid component modules using the low-temperature grid structure topology data to generate grid component module data, wherein the grid component module division includes generation module, transmission module, distribution module and user power consumption module;

[0013] Step S13: Collect power grid operation data from the low-temperature power grid based on the power grid component module data to obtain low-temperature power grid operation data; perform data preprocessing on the low-temperature power grid operation data to generate standard low-temperature power grid operation data, wherein data preprocessing includes data denoising, data filtering, data normalization and data standardization;

[0014] Step S14: Perform three-dimensional modeling of the power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of the low-temperature power grid operation.

[0015] This invention, by acquiring low-temperature power grid structure data and performing topology analysis and module partitioning, comprehensively grasps the overall structure and detailed characteristics of the low-temperature power grid, dividing it into generation, transmission, distribution, and user power consumption modules. This makes the composition of the power grid system clearer, facilitating subsequent targeted analysis and optimization. The acquisition and preprocessing of low-temperature power grid operation data ensures data accuracy, completeness, and consistency. Data denoising, filtering, normalization, and standardization significantly improve data quality, providing a reliable foundation for subsequent analysis and modeling. Generating a 3D model of the low-temperature power grid based on standardized operation data provides a visual representation of the grid's operating status, allowing engineers to observe and analyze key operating parameters. This visualization method helps quickly identify problems and formulate optimization measures. The partitioning into generation, transmission, distribution, and user power consumption modules helps decompose the complex power grid system into manageable and optimizable parts. Data acquisition and analysis for each module can be performed in parallel, improving overall efficiency. Through modeling and visual analysis of low-temperature power grid operation data, potential problems, such as power loss and operational anomalies, can be identified, and targeted optimization strategies can be implemented, thereby improving the power grid's operational efficiency and reliability. All steps are interconnected, and the generated 3D modeling data not only forms the basis for operation monitoring, but also provides data support and model foundation for subsequent simulation, optimization scheduling, and intelligent control.

[0016] Preferably, step S14 includes the following steps:

[0017] Step S141: Extract key operating data from the standard low-temperature power grid operation data to obtain key operating data of the low-temperature power grid, which includes operating temperature data, voltage and current data and power load data.

[0018] Step S142: Spatial positioning of power grid equipment is performed on the low-temperature power grid structure data to generate power grid equipment coordinate data; the path of the power grid equipment coordinate data is drawn to generate line route data;

[0019] Step S143: Spatial modeling of the low-temperature power grid structure data is performed using line routing data to generate low-temperature power grid spatial site layout data; spatial site data is imported from the low-temperature power grid spatial site layout data based on operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

[0020] This invention accurately captures core operational indicators of low-temperature power grids by extracting key operational data (such as operating temperature, voltage, current, and power load), highlighting the focus of data analysis. The extracted key data directly reflects the power grid's operating status, providing a reliable basis for subsequent modeling and optimization. Spatial positioning and coordinate generation of power grid equipment tightly integrates the power grid's physical structure with operational data, facilitating the location of equipment distribution within the grid. The generated line routing data clearly displays the power transmission path of the power grid, facilitating the analysis of power flow and the identification of potential bottlenecks or anomalies. Spatial modeling transforms the physical structure of the low-temperature power grid into intuitive 3D layout data, enhancing the system's visualization and enabling engineers to clearly understand the power grid structure and site distribution. Importing key data such as operating temperature, voltage, current, and power load into the spatial site layout further enriches the practicality of 3D modeling, providing a more realistic and dynamic operational model. The 3D modeling data integrates the power grid's spatial structure with operational data, enabling multi-dimensional monitoring of power grid operation. Engineers can quickly detect equipment anomalies, line faults, and other problems through the model, improving troubleshooting efficiency. The generation of 3D models not only visualizes static structures but also provides data support for subsequent simulations, dynamic optimization scheduling, and load allocation, helping to improve the overall operational efficiency and stability of the power grid. The clear breakdown of steps facilitates parallel processing of operational data extraction, equipment location, path delineation, and 3D modeling by different teams, improving project implementation efficiency. The generated 3D modeling data can serve as a foundational module for subsequent data analysis, prediction, and optimization, supporting further expansion and application.

[0021] Preferably, step S2 includes the following steps:

[0022] Step S21: Based on the preset abnormal index threshold, perform power grid anomaly monitoring on the three-dimensional modeling data of low temperature power grid operation to obtain low temperature power grid anomaly monitoring data;

[0023] Step S22: Based on the abnormal monitoring data of the low-temperature power grid, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation;

[0024] Step S23: Perform a hierarchical abnormal operation impact analysis on the low-temperature power grid operation anomaly module to generate low-temperature power grid operation anomaly impact factors;

[0025] Step S24: Perform cascaded fault propagation analysis on the low-temperature power grid operation anomaly module through the low-temperature power grid operation anomaly influencing factors, and generate power grid cascaded power fault propagation data.

[0026] This invention monitors 3D modeling data of low-temperature power grid operation based on preset anomaly thresholds, enabling rapid detection of abnormal phenomena such as excessive temperature, voltage anomalies, or load imbalances. Automated monitoring reduces the need for manual intervention, improves anomaly detection efficiency, and provides timely warnings. Based on the anomaly monitoring data, the 3D modeling data is used to screen for anomalous modules, identifying specific affected modules (such as generation and transmission modules), thus pinpointing the problem to a specific area or device. The identified anomalous modules allow for targeted analysis, avoiding data redundancy and resource waste. Layered impact analysis of anomalous modules reveals their specific impact on power grid operation from multiple dimensions (such as equipment, line, and system levels). The generated anomaly impact factors provide quantitative reference indicators, laying the foundation for subsequent optimization and repair work. Cascaded fault propagation analysis using anomaly impact factors simulates how the impact of anomalous modules propagates through the power grid, generating cascaded power fault propagation data. This analysis method can predict potential systemic risks in advance, preventing large-scale power outages or system collapses caused by single-point faults. This entire process chain ensures full coverage from anomaly monitoring to fault propagation analysis, effectively improving the safety and stability of power grid operation. By detecting and predicting propagation paths early, operators can develop targeted fault isolation or repair strategies to prevent problems from escalating. The generated low-temperature power grid anomaly monitoring data, anomaly influencing factors, and fault propagation data provide data support for the intelligent operation optimization of the power grid, helping to develop more efficient scheduling algorithms and fault handling solutions.

[0027] Preferably, step S23 includes the following steps:

[0028] Step S231: Collect basic power generation data from the power generation module in the low-temperature power grid operation anomaly module to obtain basic power generation module data; perform power generation cooling analysis on the basic power generation module data to generate power generation module cooling data; and perform first influencing factor transformation on the basic power generation module data based on the power generation module cooling data to generate power generation module influencing factors.

[0029] Step S232: Collect basic transmission data for the transmission module in the low-temperature power grid operation anomaly module to obtain basic transmission module data; assess the line icing load status based on the basic transmission module data to generate transmission module line assessment data; analyze the insulation performance of the basic transmission module data using the transmission module line assessment data to generate transmission module insulation performance data; and perform a second influencing factor transformation on the basic generation module data based on the transmission module insulation performance data to generate transmission module influencing factors.

[0030] Step S233: Collect basic transmission data for the distribution module in the low-temperature power grid operation anomaly module to obtain basic distribution module data; perform power grid cooling efficiency analysis on the basic distribution module data to generate distribution cooling efficiency data; perform third influencing factor transformation on the basic distribution module data based on the distribution cooling efficiency data to generate distribution module influencing factors;

[0031] Step S234: Collect basic power consumption data from the user power consumption modules in the low-temperature power grid operation anomaly module to obtain basic power consumption module data; perform power grid load characteristic analysis on the basic power consumption module data to generate power load characteristic data; and perform fourth influencing factor transformation on the basic power consumption module data based on the power load characteristic data to generate power consumption module influencing factors.

[0032] Step S235: Integrate the influence factors of the power generation module, the power transmission module, the power distribution module, and the power consumption module to generate the low-temperature power grid operation anomaly influence factor.

[0033] This invention ensures comprehensive recording of critical operating states of abnormal modules through independent basic data collection for power generation, transmission, distribution, and user power consumption modules. The module-based data collection strategy effectively avoids data omissions and provides detailed and accurate data support for subsequent analysis. Cooling data reveals the operating efficiency and temperature control capabilities of power generation modules in low-temperature environments, helping to identify key factors affecting power generation efficiency. The converted impact factors quantify the impact of cooling on power generation module performance, providing a reference for subsequent optimization. Icing load assessment and insulation performance analysis can identify reliability issues of transmission lines in extreme low-temperature environments. The converted transmission module impact factors quantify the specific impact of low temperatures on line transmission performance, supporting line optimization design. Cooling efficiency analysis reveals the heat dissipation efficiency and operational stability of distribution modules in low-temperature environments. The converted impact factors reflect the potential impact of cooling performance on power distribution, contributing to optimized distribution design. Load characteristic analysis delves into the power consumption behavior and power demand characteristics of users in low-temperature environments. The converted impact factors provide quantitative indicators of user-end operating status, facilitating the rational allocation of grid resources. By integrating the influencing factors of power generation, transmission, distribution, and user power consumption modules, an influencing factor for abnormal operation of the power grid in low temperatures is generated, comprehensively reflecting the overall characteristics of abnormal grid operation. The integration of influencing factors helps to assess the multifaceted impact of the low-temperature environment on the power grid from a global perspective, providing a scientific basis for the formulation of optimization strategies. Through modular data collection, stepwise analysis, and factor integration, the sources and diffusion paths of anomalies are systematically analyzed. Accurate identification of the main influencing factors of anomalies provides a direction for precise intervention in power grid management.

[0034] Preferably, step S24 includes the following steps:

[0035] Step S241: Detect thresholds for the influencing factors of abnormal operation of the low-temperature power grid to generate fault source location data; classify the fault source location data into fault types to generate fault feature data; assess the severity of the fault feature data to generate fault level data.

[0036] Step S242: Perform connectivity analysis on the low-temperature power grid structure topology data to generate network connection data; perform propagation path prediction on the fault level data and network connection data to generate path prediction data; perform propagation time series analysis on the path prediction data to generate time series feature data.

[0037] Step S243: Perform fault propagation simulation on the path prediction data based on the time series feature data to generate propagation process data; perform spatiotemporal evolution analysis on the propagation process data to generate evolution pattern data; use the evolution pattern data to calculate the influence domain of the low-temperature power grid operation anomaly module to generate power grid cascaded power fault propagation data.

[0038] This invention accurately identifies the initiation location of faults and generates fault source location data by threshold detection of factors affecting abnormal operation of low-temperature power grids. The fault source location data is used to classify fault types, generating detailed fault characteristic data (such as short circuit, overload, or line breakage). The impact of the fault on the overall power grid is assessed by combining the fault characteristic data, generating graded fault level data (such as minor, moderate, and severe). Connectivity analysis is performed on the topology data of the low-temperature power grid structure to generate network connection data and clarify the fault propagation path. The fault level data and network connection data are combined to predict the fault propagation path, generating path prediction data. Dynamic analysis of the path prediction data generates time-series characteristic data containing fault propagation speed and temporal characteristics. Based on the power grid topology and fault level data, the affected areas and paths are accurately predicted. This provides support for the development of dynamic response plans and reduces the secondary impact of fault propagation. The time-series characteristic data allows for the early estimation of the propagation range and duration, supporting the early deployment of prevention and control measures. Spatiotemporal evolution reveals potential fault propagation patterns, providing a basis for subsequent optimization design and prevention. Based on impact domain calculation, the actual impact of faults on different modules or regions is quantified, supporting precise decision-making.

[0039] Preferably, step S3 includes the following steps:

[0040] Step S31: Divide the power grid cascade power fault propagation data into a dataset to generate a model training set and a model test machine; use the random forest algorithm to train the model on the training set to generate a pre-model for power grid cascade fault risk assessment.

[0041] Step S32: Optimize and iterate the pre-model for power grid cascade fault risk assessment using the model test set to generate a power grid cascade fault risk assessment model; import the power grid cascade power fault propagation data into the power grid cascade fault risk assessment model to predict power fault risks and generate power grid power fault risk prediction data.

[0042] Step S33: Label the fault risk level of the cascaded power fault propagation data of the power grid according to the power grid fault risk prediction data, and generate the cascaded power fault risk level of the power grid; use the power grid cascaded control optimization formula to optimize the cascaded power fault risk level of the power grid, and generate the cascaded operation optimization data of the power grid.

[0043] Step S34: Based on the power grid cascade operation optimization data, construct a power grid operation optimization scheme for the risk level of cascaded power faults, thereby generating a power grid cascaded fault operation optimization scheme.

[0044] This invention ensures the independence of model training and testing through reasonable data partitioning, thereby improving the model's generalization ability. The random forest algorithm's strong processing capability for multi-dimensional data ensures the high accuracy and robustness of the generated pre-model. The optimization iteration process enables the model to adapt to different power grid operation scenarios and data characteristics. Predicted data provides a reliable basis for subsequent risk management and fault prevention. Based on risk level-labeled data, targeted optimization of power grid operation improves resource utilization efficiency. By balancing risk, safety, and cost through control formulas, the reliability and economy of power grid operation are ensured. The optimization scheme comprehensively considers power grid operating efficiency, fault prevention, and recovery speed. The scheme construction utilizes deep mining of optimization data to provide reliable operating strategies for the smart grid. Through data-driven methods, a high-precision evaluation model is built to achieve efficient prediction and classification of power fault risks. By comprehensively considering risk level, control costs, and safety, optimization schemes are formulated to improve the stability and reliability of power grid operation. Combining risk prediction and optimization schemes, the power grid can take preventative measures before faults occur, reducing the scope and losses of accidents. By utilizing machine learning techniques and optimization algorithms, the power grid operation is promoted towards intelligence, improving the overall operation and maintenance level. The comprehensive optimization process takes into account both operational safety and economy, and has built a low-cost, high-return power grid management system.

[0045] Preferably, the optimization formula for grid cascade control in step S33 is as follows:

[0046]

[0047] In the formula, Let w represent the target value for optimizing cascaded operation of the power grid, where N represents the total number of power grid nodes. i Let P be the importance weight coefficient of the i-th node. i,actual Let P be the actual power of the i-th node. i,max Let ΔP be the maximum allowable power of the i-th node. i This is represented as the power fluctuation at the i-th node. Let t represent the time derivative of the power change at the i-th node, t represent the power change time, α represent the weighting coefficient of the power fluctuation, and β represent the weighting coefficient of the power change rate.

[0048] This invention analyzes and integrates a power grid cascade control optimization formula, which integrates multiple key factors, including: node importance weight w. i By assigning weights, priority is given to nodes critical to grid operation, ensuring that important nodes are optimized first. Power utilization rate This reflects the ratio of a node's actual power to its capacity, preventing node overload or resource waste. Power fluctuation ΔP iCapture short-term power fluctuations to reduce the risk of failures caused by these fluctuations. Power change rate. By focusing on the rate of power change, sudden fluctuations in the power grid can be controlled. This is achieved by introducing the time derivative. The formula possesses dynamic optimization capabilities, enabling it to capture rapid changes in the power grid state in real time, adapt to complex operating environments, and improve the timeliness and accuracy of control. By comprehensively considering power fluctuations and their rates of change, the formula can provide early warnings of cascading faults and prioritize the resolution of high-risk nodes during optimization, significantly reducing the level of power grid fault risk. Optimization target value The calculation comprehensively considers power allocation and node importance weights to achieve optimal resource allocation and improve the overall operating efficiency of the power grid. The parameters in the formula (such as α, β, and weight w) i It has adjustment range and can be flexibly adjusted according to different power grid operation needs, thus being suitable for power grid systems of various sizes and complexities. While conventional power grid cascade control optimization formulas in the field can yield the target value for power grid cascade operation optimization, the power grid cascade operation optimization formula provided by this invention can calculate the target value for power grid cascade operation optimization more accurately. This formula, by quantifying and optimizing multiple key indicators of power grid operation, can improve the operating efficiency and control flexibility of the power grid while ensuring safety and reliability, and is particularly suitable for the operation optimization tasks of complex cascaded power grids.

[0049] Preferably, step S4 includes the following steps:

[0050] Step S41: Collect operation feedback data based on the power grid cascade fault operation optimization scheme to obtain power grid cascade fault operation optimization feedback data; evaluate the operation optimization performance of the power grid cascade fault operation optimization feedback data to generate power grid operation optimization performance evaluation data;

[0051] Step S42: Update the power grid cascade fault operation optimization scheme using the power grid cascade fault operation optimization feedback data, and generate a power grid cascade fault operation optimization update scheme to execute the low temperature power grid operation optimization operation.

[0052] This invention forms a closed-loop process for power grid operation optimization through operational feedback data collection and performance evaluation in step S41. This feedback mechanism can promptly capture potential problems in power grid operation and evaluate the actual effectiveness of optimization schemes, ensuring the reliability and continuous improvement of optimization schemes. The collection and performance evaluation of operational feedback data provide high-quality basic data for updating optimization schemes. Using this data, step S42 can dynamically adjust the optimization strategy, making the optimization scheme more aligned with actual operational needs and enhancing the power grid's adaptability to variable operating environments (such as low-temperature environments). By continuously updating the power grid cascading fault operation optimization scheme, potential cascading fault risks can be effectively identified and mitigated. Especially under low-temperature operating conditions, this step can adjust the scheme based on feedback to ensure power grid stability and reduce the probability of faults caused by extreme environments. The synergistic effect of optimization performance evaluation (S41) and scheme update (S42) helps to identify efficiency bottlenecks in operation and resolve them through scheme adjustments, thereby achieving optimal allocation of power grid resources and improving overall operational efficiency. Through a specialized design for optimizing low-temperature power grid operation, step S42 can adjust according to the characteristics of the power grid under low-temperature conditions (such as load fluctuations and increased cable losses), ensuring that the power grid can still operate safely and efficiently under extreme weather conditions. This step, by combining feedback data and optimized performance evaluation, realizes an automated scheme update process, introduces an intelligent decision-making mechanism for power grid operation, and improves the automation and intelligence level of operation control.

[0053] This specification provides a low-temperature power grid operation safety monitoring system based on intelligent algorithms, used to execute the aforementioned low-temperature power grid operation optimization method based on intelligent algorithms. The low-temperature power grid operation safety monitoring system based on intelligent algorithms includes:

[0054] The power grid modeling module is used to acquire low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; and perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of low-temperature power grid operation.

[0055] The cascaded fault analysis module is used to filter abnormal modules in the three-dimensional modeling data of low-temperature power grid operation based on preset abnormal index thresholds to obtain abnormal modules of low-temperature power grid operation; perform hierarchical abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal operation impact factors of low-temperature power grid operation; and perform cascaded fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal operation impact factors of low-temperature power grid operation to generate cascaded power fault diffusion data of the power grid.

[0056] The power grid operation optimization module is used to predict power fault risks from cascaded power fault propagation data and generate power grid power fault risk prediction data; to optimize the cascaded operation of the cascaded power fault propagation data based on the power grid power fault risk prediction data and generate cascaded operation optimization data; and to construct power grid operation optimization schemes based on the cascaded operation optimization data, thereby generating cascaded fault operation optimization schemes.

[0057] The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascade fault operation optimization scheme and generate power grid operation optimization performance evaluation data; it also uses the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

[0058] The beneficial effects of this invention lie in ensuring the systematic and hierarchical nature of the power grid by acquiring low-temperature power grid structure data and dividing the power grid into constituent modules. By collecting power grid operation data and performing 3D modeling, low-temperature power grid operation data is generated, improving the visualization and accuracy of power grid operation. This helps to comprehensively understand the power grid's operating status and potential problems, thus laying the foundation for subsequent optimization and fault analysis. By screening abnormal modules based on preset abnormal indicator thresholds, potential fault areas in the power grid can be identified in a timely manner, thereby avoiding the risk of grid-wide outages. Through hierarchical anomaly impact analysis and cascaded fault propagation analysis, this module effectively predicts and tracks fault propagation paths, accurately assesses the scope and degree of fault impact, and improves the accuracy of fault detection early warning and response strategies. Through the prediction of power fault risks and cascaded operation optimization, the risk of large-scale power grid failures is effectively reduced. By constructing power grid operation optimization schemes, the operation of the power grid can be dynamically adjusted, power grid resource allocation can be optimized, and the operating efficiency and stability of the power grid in low-temperature environments can be improved, providing a guarantee for the sustainability of power grid operation. Performance evaluation of the power grid operation optimization schemes can measure the effectiveness of the optimization schemes and provide a basis for subsequent scheme improvements. By updating the optimization scheme using feedback data, the power grid's efficient response capability under different operating environments and fault conditions is ensured. Through continuous optimization, the overall operating efficiency, fault response capability, and energy utilization rate of the power grid are improved. Therefore, this invention enhances the safety and intelligence of cryogenic power grid operation through intelligent modular analysis, fault propagation prediction and optimization, and a real-time feedback mechanism. Attached Figure Description

[0059] Figure 1 This is a flowchart illustrating the steps of a method for optimizing the operation of a cryogenic power grid based on intelligent algorithms.

[0060] Figure 2 for Figure 1A detailed flowchart illustrating the implementation steps of step S2.

[0061] Figure 3 for Figure 1 A detailed flowchart illustrating the implementation steps of step S3.

[0062] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0064] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0065] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0066] To achieve the above objectives, please refer to Figures 1 to 3 A method for optimizing the operation of a low-temperature power grid based on intelligent algorithms, the method comprising the following steps:

[0067] Step S1: Obtain low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate low-temperature power grid operation three-dimensional modeling data.

[0068] Step S2: Based on preset abnormal index thresholds, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation; the abnormal modules of the low-temperature power grid operation are subjected to hierarchical abnormal operation impact analysis to generate the abnormal operation impact factors of the low-temperature power grid operation; the abnormal operation impact factors of the low-temperature power grid operation are used to perform cascade fault propagation analysis on the abnormal modules of the low-temperature power grid operation to generate cascade power fault propagation data of the power grid.

[0069] Step S3: Perform power fault risk prediction on the cascaded power fault propagation data of the power grid to generate power grid power fault risk prediction data; perform cascade operation optimization on the cascaded power fault propagation data of the power grid based on the power grid power fault risk prediction data to generate power grid cascade operation optimization data; construct a power grid operation optimization scheme based on the power grid cascade operation optimization data to generate a power grid cascaded fault operation optimization scheme.

[0070] Step S4: Based on the power grid cascade fault operation optimization scheme, conduct an operation optimization performance evaluation and generate power grid operation optimization performance evaluation data; use the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

[0071] This invention, through modular partitioning and 3D modeling of low-temperature power grid structure data, provides a comprehensive and detailed understanding of the power grid's composition, operating status, and structural characteristics. This provides accurate foundational data for subsequent data acquisition, fault analysis, and optimization, ensuring a true reflection of the power grid's operating status and facilitating further optimization efforts. Anomaly filtering modules based on preset anomaly index thresholds can accurately identify potential fault sources in low-temperature power grid operation. Through hierarchical analysis and cascaded fault propagation, it can reveal fault propagation paths and impact ranges, predicting potential risk areas in the power grid in advance, thus providing precise basis for subsequent fault prediction and optimization, and preventing large-scale power outages. Power fault risk prediction can identify high-risk areas faced by the power grid under low-temperature conditions in advance and make dynamic adjustments. Through cascaded operation optimization, it can effectively avoid or reduce fault propagation, improve the power grid's fault tolerance and stability, ensure stable operation of the power grid in complex environments, and avoid large-scale power outages. Performance evaluation of optimization schemes can quantify the effectiveness of optimization schemes, ensuring the feasibility and effectiveness of operational optimization. By utilizing optimized feedback data to update the system, it is possible to dynamically adapt to changes in the actual operation of the power grid, ensuring that the power grid maintains its optimal operating state in low-temperature environments and improving the system's flexibility and ability to respond to emergencies. Therefore, this invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault propagation prediction and optimization, and a real-time feedback mechanism.

[0072] In this embodiment of the invention, reference is made to Figure 1 The diagram shown illustrates the steps of a method for optimizing the operation of a low-temperature power grid based on an intelligent algorithm, according to the present invention. In this example, the method includes the following steps:

[0073] Step S1: Obtain low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate low-temperature power grid operation three-dimensional modeling data.

[0074] In this embodiment of the invention, real-time data is collected by sensors (such as temperature sensors, current sensors, voltage sensors, etc.) deployed in the cryogenic power grid. These sensors provide operational status data for various parts of the power grid, such as equipment load, temperature, humidity, and current. Geographical location data of power grid equipment (including power transformers, transmission lines, switching equipment, etc.) is collected. This location data is obtained through GPS positioning, map data, or a known power grid geographic information system (GIS). Based on power grid design drawings, GIS, construction documents, etc., the basic topology of the power grid is obtained, such as the nodes and connections of substations, transmission lines, access equipment, and distribution networks. Data from sensors, equipment locations, and topology are fused to form a complete cryogenic power grid structure dataset. Data collected from various sensors and equipment is ensured to have a unified timestamp for subsequent data processing and analysis. Based on the functions of different equipment in the power grid (such as transmission, transformation, and distribution), the power grid is divided into multiple functional modules, such as substation modules, transmission modules, and distribution modules. The power grid is also divided into multiple regional modules based on geographical regions or power grid operating areas. Each regional module includes all power grid equipment and connections within that region. The system is divided into modules based on equipment type (e.g., switchgear, transformers, battery storage devices, etc.) to ensure that each module contains associated equipment and communication units. After module division, each module is assigned a unique identifier, and detailed parameters (e.g., voltage level, load capacity, transmission capacity, etc.) are provided for the equipment and connections within each module. The connection relationships between different modules are recorded (e.g., current flow and power supply capacity between substation and distribution modules), and clear input / output interfaces are defined for each module. The data structures after module division are integrated to generate a set of power grid component module data, which can be used for subsequent power grid operation monitoring, data analysis, and optimization. Sensors are deployed in each power grid module to monitor the operating status of each module in real time, including current, voltage, temperature, equipment operating status, and fault diagnosis data. Based on the real-time requirements of the power grid, a data acquisition frequency (e.g., once per minute or hour) is set to ensure sufficiently detailed power grid operation data is obtained. Real-time operating data from each module in the power grid is collected, including equipment operating status (e.g., switch status, load conditions), temperature, voltage, current, and other key parameters. During the data acquisition process, the equipment status is analyzed in real time to determine if any anomalies exist (such as equipment overload or overheating), and this anomaly information is fed back to the monitoring system in real time. The collected raw data is cleaned (noise removal, missing data processing, etc.) and converted to a standard format. Based on the standard operating specifications of the power grid, a standard cryogenic power grid operation dataset is generated, including real-time operating data, status information, and any anomalies for each module. The cryogenic power grid topology is combined with geographic location data, and a GIS system is used to accurately locate the power grid equipment in three-dimensional space.The process transforms the data of power grid components and equipment (such as nodes, connections, and loads) into visualized 3D model data. Based on the power grid component data and geographic information, a 3D spatial structure model of the power grid is constructed using modeling software (such as AutoCAD, Revit, or other power engineering modeling tools). The model includes various power grid equipment (such as transformers, switches, and transmission lines) and their precise locations in 3D space. Real-time display of equipment status in the 3D model is achieved based on power grid operation data (such as load, current, and voltage), helping power grid operators monitor equipment operation status in real time. This generates 3D modeling data of power grid operation, including power grid structure, equipment parameters, operating status, and environmental factors (such as temperature and humidity). This data can be used for further power grid analysis, fault diagnosis, and performance optimization.

[0075] Step S2: Based on preset abnormal index thresholds, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation; the abnormal modules of the low-temperature power grid operation are subjected to hierarchical abnormal operation impact analysis to generate the abnormal operation impact factors of the low-temperature power grid operation; the abnormal operation impact factors of the low-temperature power grid operation are used to perform cascade fault propagation analysis on the abnormal modules of the low-temperature power grid operation to generate cascade power fault propagation data of the power grid.

[0076] In this embodiment of the invention, abnormal indicators (such as temperature, load, voltage, current, equipment status, communication delay, etc.) are defined as monitoring indicators. The threshold for each indicator should be set based on the power grid's design standards and historical operating data. For example, a transformer temperature exceeding 70°C will trigger a fault warning, and voltage fluctuations exceeding ±10% will affect the stability of the power grid. Specific thresholds are set for each indicator (e.g., a temperature threshold of 70°C, a current threshold of 120% of the rated current), and equipment or modules exceeding these thresholds are considered abnormal. By analyzing the three-dimensional modeling data of the low-temperature power grid operation, each module is compared with the preset abnormal indicator thresholds. If a module's indicator exceeds the preset threshold, it is marked as an abnormal module. All modules exceeding the thresholds are selected, including transformers, distribution equipment, transmission lines, switching equipment, etc., forming a set of abnormal modules for low-temperature power grid operation. The generated abnormal module data includes the module identifier where the abnormality occurred, the indicator value, the threshold, the abnormal time point, etc. This data provides the basis for subsequent analysis. Based on the power grid's structure and operating mode, the abnormal modules are layered. Typical layering methods include equipment layer, subsystem layer, and regional layer. Anomalies at different levels have varying impacts on the power grid. **Equipment Level:** Failures of individual devices, such as transformers, switchgear, and energy storage devices. **Subsystem Level:** Subsystems composed of multiple devices (e.g., distribution networks, transmission networks, substations). **Regional Level:** Regional faults in the power grid, such as power outages in a specific area. Multiple influencing factors are defined to describe the severity of the anomaly. Examples include: the impact of load changes caused by an abnormal module on other modules; the impact of temperature increases caused by equipment anomalies on adjacent equipment; and the impact of abnormal voltage or current on other equipment. Each influencing factor is assigned a different weight based on its contribution to grid stability. For example, current fluctuations have a higher weight, while temperature fluctuations have a lower weight. Each abnormal device is analyzed to calculate its impact on adjacent equipment. For example, excessive transformer temperature causing overload in nearby equipment affects the overall stability of the power grid. The impact of abnormal operation of an entire subsystem (e.g., a substation) on the surrounding area is analyzed to assess the scope of the power supply impact. When multiple subsystems or devices fail simultaneously, the impact at the regional level of the power grid is assessed, generating anomaly impact factors for the power grid region. Based on the analysis results at the equipment, subsystem, and regional levels, operational impact factor data for each abnormal module is generated, including the degree of impact, scope of impact, and severity rating at different levels. Cascading failure refers to a failure in one module causing failures in other connected modules, ultimately spreading to the entire power grid. A cascading failure propagation model is established to simulate the diffusion process after a failure occurs. Based on the power grid topology, the connection relationships between each module and other modules are defined, forming a fault propagation network. Each module in the power grid is a node in the network, and connections are the paths for power flow.Based on the power grid topology and the impact factors of anomalous modules, the simulation demonstrates how a fault propagates from one module to others. The speed and path of fault propagation depend on the impact factors of the anomalous modules and network connectivity. For example, when a current anomaly occurs in a substation, the fault can be transmitted to downstream areas via transmission lines. The scope and affected areas of fault propagation are assessed based on the power grid structure and impact factors. If a voltage anomaly in one area propagates to neighboring areas, it will affect more equipment and systems. Information such as the occurrence time, propagation path, affected modules, and fault scale of cascaded faults is recorded. This data can be used for further power grid restoration and optimization analysis. By calculating the total impact of fault propagation (such as lost load, affected areas, and the number of affected devices), data support is provided for subsequent restoration and repair work.

[0077] Step S3: Perform power fault risk prediction on the cascaded power fault propagation data of the power grid to generate power grid power fault risk prediction data; perform cascade operation optimization on the cascaded power fault propagation data of the power grid based on the power grid power fault risk prediction data to generate power grid cascade operation optimization data; construct a power grid operation optimization scheme based on the power grid cascade operation optimization data to generate a power grid cascaded fault operation optimization scheme.

[0078] In this embodiment of the invention, key factors influencing power fault risk are identified in the cascaded fault propagation data of the power grid, such as load fluctuations, equipment health status, communication delays, and environmental factors (e.g., temperature, humidity). Historical fault records of the power grid are collected and analyzed to establish a database containing the conditions for different types of fault occurrences, providing reference data for fault risk prediction. A fault risk prediction model is constructed using methods such as Bayesian networks, Markov chains, random forests, or neural networks to predict the probability of fault occurrence. The model is trained and inferred based on information such as the power grid topology, historical fault data, and current operating status. The cascaded fault propagation data of the power grid is preprocessed, including data cleaning, outlier removal, and normalization, to ensure the quality of the model input data. The risk prediction model analyzes the cascaded power fault propagation data of the power grid and outputs the fault risk level for each module or region. The output data includes: the probability of fault occurrence, the impact range of potential fault modules, and affected equipment, generating power grid fault risk prediction data, including the probability of risk prediction, warning level, and potential fault areas. This data can provide a basis for subsequent power grid optimization and fault prevention. The main objective of power grid cascade operation optimization is to minimize the risk of fault propagation, ensuring that faults do not spread throughout the grid or that their impact is limited to a minimum. It also aims to ensure the grid maintains load balance and system stability during operation, avoiding widespread power outages. One optimization objective is to extend the lifespan of grid equipment, reduce peak loads, and prevent overload or overheating. Genetic algorithms can be used to optimize the grid topology, enabling the reconfiguration of lines or equipment to reduce fault propagation during fault occurrences. Particle swarm optimization algorithms can be used to dynamically adjust grid load distribution and optimize load flow to reduce the impact of faults on the entire system. For topology optimization of grid operation, MILP models can be used to comprehensively optimize various components of the grid (such as substations, transmission lines, load distribution, etc.) to ensure optimal operating strategies. In the event of a fault, the grid's automatic reconfiguration system transfers loads from the faulty area to other healthy areas. The optimization process should be based on power load, system stability, and risk prediction data, prioritizing paths unaffected by the fault. By employing a power grid load flow optimization algorithm, the distribution of power flow is dynamically adjusted to prevent excessive load in localized areas during faults, which could lead to cascading effects or system collapse. Through topology reconfiguration and fault isolation, the power grid structure is optimized to ensure that power flow can bypass faulty areas and restore power supply via backup paths. This generates optimized power grid topology data, including reconfiguration of grid components, load allocation, fault isolation, and recovery paths. Parameters from the optimization process are output, such as load adjustment values, equipment scheduling strategies, and the operating status of various grid modules.The goal of the power grid operation optimization scheme is to ensure rapid isolation of fault areas and optimized load distribution in the event of a fault through real-time monitoring and automated control, thereby maximizing grid stability and minimizing fault losses. Based on power grid cascade operation optimization data, an automated control response mechanism is designed to ensure rapid load adjustment and grid reconfiguration in the event of a fault. A fault detection system is designed to monitor equipment status, load fluctuations, voltage changes, and other information in the power grid in real time, promptly identifying potential fault risks. After a fault occurs, an optimization algorithm automatically plans a recovery path, quickly switching from the fault area to a healthy area to ensure uninterrupted power supply. A distributed control system is used to control various parts of the power grid in real time, ensuring that other parts of the grid continue to operate stably in the event of a local fault. The effectiveness of the power grid cascade fault operation optimization scheme is evaluated through simulation and historical data analysis, including fault response time, recovery efficiency, and system stability. The optimization scheme is adjusted based on the evaluation results to further improve the power grid's disaster resistance, stability, and operational efficiency. Based on the aforementioned optimization process, a complete power grid cascade fault operation optimization scheme is generated, including fault detection, emergency response, automated recovery paths, and load adjustment strategies.

[0079] Step S4: Based on the power grid cascade fault operation optimization scheme, conduct an operation optimization performance evaluation and generate power grid operation optimization performance evaluation data; use the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

[0080] In this embodiment of the invention, the goal of power grid operation optimization performance evaluation is to assess various indicators of the power grid, such as response speed, fault recovery capability, system stability, and load allocation efficiency, after implementing the optimization scheme. The main evaluation indicators include: whether the optimization scheme can respond promptly to fault occurrences and shorten fault handling response time; whether the optimization scheme can effectively shorten the time for the power grid to return to normal operation; whether the stability of the power grid improves after the implementation of the optimization scheme, maintaining normal operation and avoiding large-scale outages; and whether the load allocation is reasonable under the optimization scheme, avoiding overload or inefficient operation. Simulation tools are used to conduct virtual power grid operation tests, simulating different types of faults and external interference to evaluate the actual effect of the optimization scheme. Simulations include single-point faults, multi-point faults, and sudden load fluctuations. Small-scale on-site tests of the optimization scheme are conducted in selected areas or modules, monitoring the power grid response, fault recovery, and load allocation in real time, and collecting on-site data for evaluation. The evaluation data after the implementation of the optimization scheme is compared with the data from the original unoptimized state to analyze the improvement of various indicators. The above evaluation methods generate power grid operation optimization performance evaluation data, including data on various evaluation indicators such as response time, fault recovery time, grid stability, and load distribution efficiency. This data can be used to determine the effectiveness and performance of the optimization scheme. A detailed performance evaluation report is generated, listing the changes before and after the implementation of the optimization scheme to help decision-makers understand its effects. During power grid operation, real-time feedback data after the implementation of the optimization scheme is collected. This data includes equipment status, load fluctuations, fault frequency, system response time, and recovery time. Real-time data on the power grid under different operating conditions, such as current, voltage, temperature, and load distribution, are collected through installed monitoring equipment to provide feedback on the actual operation of the power grid. Feedback from power users is collected, especially their reactions to power supply interruptions and restorations, to assess the impact of the optimization scheme on users. The feedback data after optimization implementation is analyzed to identify potential shortcomings of the optimization scheme. For example, excessively long fault recovery times in some areas or excessive loads on some equipment. Through comprehensive analysis of the feedback data, problems existing in the implementation of the optimization scheme are identified, such as slow response of some equipment, incomplete fault isolation, or uneven load distribution. Based on the feedback data and evaluation results, it is confirmed which optimization measures have played a positive role and which need further improvement. Based on feedback, adjustments and optimizations were made to address identified problems. For example, load allocation strategies were optimized, grid topology was adjusted, or fault detection and automated response capabilities were strengthened. Based on actual operating conditions, optimization algorithms (such as genetic algorithms and particle swarm optimization) were improved to better adapt to the actual operational needs of the grid. Equipment scheduling strategies were adjusted to address response delays or overloads in certain devices, achieving a more balanced load distribution. Emergency response mechanisms were optimized to address untimely responses in certain areas, ensuring rapid isolation and power restoration in the event of a fault.Based on the feedback data and analysis results, an updated optimization plan for cascading power grid fault operation is generated. The updated plan should include new optimization strategies, adjusted algorithms, and improved equipment scheduling strategies.

[0081] Preferably, step S1 includes the following steps:

[0082] Step S11: Obtain cryogenic power grid structure data;

[0083] Step S12: Perform grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; divide the low-temperature grid structure data into grid component modules using the low-temperature grid structure topology data to generate grid component module data, wherein the grid component module division includes generation module, transmission module, distribution module and user power consumption module;

[0084] Step S13: Collect power grid operation data from the low-temperature power grid based on the power grid component module data to obtain low-temperature power grid operation data; perform data preprocessing on the low-temperature power grid operation data to generate standard low-temperature power grid operation data, wherein data preprocessing includes data denoising, data filtering, data normalization and data standardization;

[0085] Step S14: Perform three-dimensional modeling of the power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of the low-temperature power grid operation.

[0086] In this embodiment of the invention, structural data is acquired from sensors, data acquisition devices, and historical archives of the cryogenic power grid. The data ensures coverage of the main components of the power grid, including power generation units, transmission and distribution lines, switching equipment, and user terminal connections. The data format must support multi-dimensional descriptions, including geometric layout, physical parameters (such as resistance and capacitance), and environmental influencing factors (such as temperature and humidity). Graph theory methods are applied to construct a topology graph of the cryogenic power grid based on nodes (power grid components) and edges (electrical connections between components); topology characteristics, such as network diameter, connectivity, and redundancy, are determined to assess network robustness. Based on the power grid's function and topology, it is divided into power generation modules, transmission modules, distribution modules, and user power consumption modules; module partitioning algorithms (such as community detection algorithms) are used to ensure logical consistency and physical rationality of connections between modules; module data is output, including module boundaries, a list of devices within a module, and connection relationships between modules. Distributed sensor networks are used to collect cryogenic power grid operating status data, including real-time voltage, current, power, and frequency; the acquisition frequency is ensured to be high enough to capture dynamic operating characteristics. Noise is removed using wavelet transform or low-pass filters; signal quality is optimized using Kalman filters; data is converted to a uniform scale for easier subsequent processing and analysis. The generated standard cryogenic power grid operation data exhibits consistency and high reliability, supporting modeling requirements. A 3D model based on physical laws and data-driven principles is constructed using the standard cryogenic power grid operation data. The 3D modeling must consider the time dimension, generating a panoramic view of the dynamic operation scenario. Simulation tools (such as MATLAB Simulink, ANSYS, or a self-developed simulation platform) are used to create the model. The 3D modeling data for cryogenic power grid operation includes the spatial location, operating status, and dynamic change characteristics of power grid components. The model should possess high visualization and interactivity to support subsequent optimization and decision-making.

[0087] Preferably, step S14 includes the following steps:

[0088] Step S141: Extract key operating data from the standard low-temperature power grid operation data to obtain key operating data of the low-temperature power grid, which includes operating temperature data, voltage and current data and power load data.

[0089] Step S142: Spatial positioning of power grid equipment is performed on the low-temperature power grid structure data to generate power grid equipment coordinate data; the path of the power grid equipment coordinate data is drawn to generate line route data;

[0090] Step S143: Spatial modeling of the low-temperature power grid structure data is performed using line routing data to generate low-temperature power grid spatial site layout data; spatial site data is imported from the low-temperature power grid spatial site layout data based on operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

[0091] In this embodiment of the invention, real-time records from temperature sensors are obtained from standard cryogenic power grid operation data; abnormal areas are detected using temperature distribution characteristics, and hotspot areas are marked. Real-time voltage and current data are extracted according to line and equipment classification; dynamic curve fitting is performed on the extracted data to analyze fluctuation characteristics. Based on user power modules and power grid load balance, total load and local load data are extracted; load factor is calculated, high-load areas and potential bottlenecks are located, and the generated key operating data of the cryogenic power grid includes key indicators of operating temperature, voltage, current, and power load, which are convenient for subsequent modeling. Power grid equipment, including transformers, switches, transmission lines, etc., is identified through power grid structure data; a three-dimensional spatial coordinate system is generated based on equipment geographic coordinate data, and power grid equipment coordinate data is output. Based on equipment coordinate data and line topology, connection paths between equipment are constructed; optimal line routes are generated using path optimization algorithms (such as Dijkstra's algorithm); line route data includes equipment connection relationships and spatial path information. Based on line route data, spatial site layout modeling of the cryogenic power grid structure is performed; site locations and functional classifications (such as substations, user sites, etc.) are determined, and cryogenic power grid spatial site layout data is generated. Key operational data (operating temperature, voltage, current, and power load) are mapped to corresponding space stations. Using a multi-level modeling method, the operational data is embedded into the station model to reflect the actual operating status, generating three-dimensional modeling data of low-temperature power grid operation, including complete space station layout and dynamic operating characteristics, supporting subsequent analysis and visualization.

[0092] As an example of the present invention, reference is made to Figure 2 As shown, in this example, step S2 includes:

[0093] Step S21: Based on the preset abnormal index threshold, perform power grid anomaly monitoring on the three-dimensional modeling data of low temperature power grid operation to obtain low temperature power grid anomaly monitoring data;

[0094] Step S22: Based on the abnormal monitoring data of the low-temperature power grid, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation;

[0095] Step S23: Perform a hierarchical abnormal operation impact analysis on the low-temperature power grid operation anomaly module to generate low-temperature power grid operation anomaly impact factors;

[0096] Step S24: Perform cascaded fault propagation analysis on the low-temperature power grid operation anomaly module through the low-temperature power grid operation anomaly influencing factors, and generate power grid cascaded power fault propagation data.

[0097] In this embodiment of the invention, thresholds for various abnormal indicators are set based on historical data, expert experience, and power grid characteristics. Examples include temperatures exceeding specific values, voltage being too low, or abnormal current fluctuations. Monitoring standards and alarm conditions are defined for each abnormal indicator (e.g., a temperature threshold of 50°C and a voltage fluctuation range of ±10%). Each monitoring data point (e.g., voltage, current, temperature) in the three-dimensional modeling data of the low-temperature power grid operation is compared item by item to identify whether it exceeds the preset threshold. Anomalies are checked at each station and module using a comparison of real-time data streams and historical data to monitor the power grid's operating status. Low-temperature power grid anomaly monitoring data is automatically generated, marking the specific areas or modules where anomalies occur. Based on the anomaly monitoring data from step S21, and combined with the structural module division of the power grid, modules with anomalies are selected. The degree of anomaly in each module is evaluated, for example, by calculating the frequency, duration, and amplitude of anomalies, to identify modules with a significant impact. The selection criteria can be based on multiple factors, such as the degree of anomaly, module importance (e.g., power generation modules or substation modules), and the risk of anomaly propagation. The system categorizes abnormal modules (e.g., generation, transmission, and distribution modules) and further classifies them according to their impact on the power grid (high, medium, and low impact), generating data on abnormal modules in low-temperature power grid operation. This data includes the module's identification, classification, degree of abnormality, and related impact analysis. The abnormal modules are then analyzed hierarchically based on their impact levels. Hierarchical analysis can be based on the module's criticality, load characteristics, and the likelihood of anomaly propagation. For example, generation modules are the most critical modules in the power grid, and their abnormalities can severely impact the entire grid, while anomalies at user terminals have limited local impact. At each level, the specific impact of abnormal modules on the overall power grid operation is analyzed, including power output, transmission and distribution line stability, and load balance. Based on the nature of the abnormal modules (e.g., current and voltage anomalies, excessively high temperatures), their direct impact factors on the power grid are calculated. These impact factors can be calculated through data regression analysis, fault simulation, or impact propagation models based on the power grid topology, generating data on low-temperature power grid operation anomaly impact factors. This quantifies the impact of different anomalies on the power grid, helping to pinpoint the fault areas requiring priority handling. Based on the low-temperature power grid operation anomaly impact factors, a power grid cascade fault propagation model is constructed. The model should consider factors such as power transmission relationships between modules, equipment redundancy, and load carrying capacity. A fault propagation model is used to analyze the impact path of an abnormal module on other modules, simulating the fault propagation process. Graph theory-based algorithms (such as fault propagation algorithms) can be used to derive the fault chain. Based on the model analysis, cascaded power fault propagation data is generated. This data shows how a fault spreads along the power grid structure from the initial fault point, ultimately affecting the entire system. During the analysis, the speed of fault propagation, the scale of the impact, and the affected power equipment are calculated to assess the vulnerability of the power grid.

[0098] Preferably, step S23 includes the following steps:

[0099] Step S231: Collect basic power generation data from the power generation module in the low-temperature power grid operation anomaly module to obtain basic power generation module data; perform power generation cooling analysis on the basic power generation module data to generate power generation module cooling data; and perform first influencing factor transformation on the basic power generation module data based on the power generation module cooling data to generate power generation module influencing factors.

[0100] Step S232: Collect basic transmission data for the transmission module in the low-temperature power grid operation anomaly module to obtain basic transmission module data; assess the line icing load status based on the basic transmission module data to generate transmission module line assessment data; analyze the insulation performance of the basic transmission module data using the transmission module line assessment data to generate transmission module insulation performance data; and perform a second influencing factor transformation on the basic generation module data based on the transmission module insulation performance data to generate transmission module influencing factors.

[0101] Step S233: Collect basic transmission data for the distribution module in the low-temperature power grid operation anomaly module to obtain basic distribution module data; perform power grid cooling efficiency analysis on the basic distribution module data to generate distribution cooling efficiency data; perform third influencing factor transformation on the basic distribution module data based on the distribution cooling efficiency data to generate distribution module influencing factors;

[0102] Step S234: Collect basic power consumption data from the user power consumption modules in the low-temperature power grid operation anomaly module to obtain basic power consumption module data; perform power grid load characteristic analysis on the basic power consumption module data to generate power load characteristic data; and perform fourth influencing factor transformation on the basic power consumption module data based on the power load characteristic data to generate power consumption module influencing factors.

[0103] Step S235: Integrate the influence factors of the power generation module, the power transmission module, the power distribution module, and the power consumption module to generate the low-temperature power grid operation anomaly influence factor.

[0104] In this embodiment of the invention, basic data, including real-time monitoring data such as power generation, temperature, and flow rate, is extracted from the power generation module in the low-temperature power grid operation anomaly module. This data can be obtained from equipment such as generators, cooling systems, and transformers. The temperature and flow rate data in the basic data are analyzed to evaluate the cooling effect of the power generation module. Cooling efficiency is calculated, with particular attention paid to excessively high temperatures or insufficient flow rates, and abnormal areas are marked. Cooling data of the power generation module is generated based on the cooling effect for further analysis of influencing factors. Influence factors are calculated based on the cooling data of the power generation module, focusing primarily on the temperature sensitivity and cooling capacity of the power generation system. The specific formula for calculating the influence factors can include cooling rate, temperature deviation, etc., as input conditions to generate power generation module influence factors for comprehensive analysis of influencing factors in subsequent steps. Basic data, including real-time monitoring data such as line load, voltage, and temperature, is extracted from the transmission module in the low-temperature power grid operation anomaly module. This includes real-time status monitoring and load data of the transmission lines. The icing condition and load status of the transmission lines are evaluated, considering meteorological conditions, load, and the mechanical strength of the lines. Line evaluation data is generated based on the icing condition, and abnormal icing or overload conditions are marked. Line assessment data is used to analyze the insulation performance of transmission modules. Focusing on temperature and voltage data affecting line safety, ensuring the line operates within normal or safe ranges, insulation performance data is generated for further calculation of influence factors. Influence factors are calculated based on the transmission module insulation performance data, primarily focusing on line electrical stability and load conditions. Specific formulas (such as temperature and voltage deviations) are used to calculate influence factors, generating transmission module influence factors for subsequent comprehensive analysis. Basic data, including real-time monitoring data of current, voltage distribution, and temperature, is extracted from distribution modules in low-temperature power grid operation anomalies. This data helps assess the operating status of the distribution system. The cooling efficiency of distribution modules is analyzed, focusing on temperature and load balance. Cooling efficiency affects the lifespan and safety of distribution equipment; distribution cooling efficiency data is generated, marking insufficient cooling or excessively high temperatures. Influence factors are calculated based on the distribution module cooling efficiency data, primarily focusing on equipment temperature and load capacity. Specific formulas (such as temperature difference and voltage adjustment amplitude) are used to calculate influence factors, generating distribution module influence factors for subsequent comprehensive impact analysis. Basic data, including real-time data on load levels, voltage stability, and electricity consumption, is extracted from user power consumption modules within the low-temperature power grid operation anomaly module. The load characteristics of these modules are analyzed, with a focus on peak load, balance, and usage characteristics, generating electricity load characteristic data and identifying abnormal power consumption or excessive load fluctuations. Influence factors are calculated based on this load characteristic data, primarily focusing on the stability of electricity consumption and load changes. Specific formulas (such as the load stability index) are used to calculate these influence factors, generating user power consumption module influence factors for subsequent overall power grid impact analysis.The generated impact factors for power generation, transmission, distribution, and user power consumption modules are integrated. Weighted averaging, statistical methods, or comprehensive evaluation models are used to calculate the overall impact factors for abnormal operation of the low-temperature power grid. Taking into account the weight and importance of each impact factor, the final impact factors for abnormal operation of the low-temperature power grid are generated. These impact factors reflect the vulnerability of the entire power grid and specific repair or adjustment strategies.

[0105] Preferably, step S24 includes the following steps:

[0106] Step S241: Detect thresholds for the influencing factors of abnormal operation of the low-temperature power grid to generate fault source location data; classify the fault source location data into fault types to generate fault feature data; assess the severity of the fault feature data to generate fault level data.

[0107] Step S242: Perform connectivity analysis on the low-temperature power grid structure topology data to generate network connection data; perform propagation path prediction on the fault level data and network connection data to generate path prediction data; perform propagation time series analysis on the path prediction data to generate time series feature data.

[0108] Step S243: Perform fault propagation simulation on the path prediction data based on the time series feature data to generate propagation process data; perform spatiotemporal evolution analysis on the propagation process data to generate evolution pattern data; use the evolution pattern data to calculate the influence domain of the low-temperature power grid operation anomaly module to generate power grid cascaded power fault propagation data.

[0109] In this embodiment of the invention, threshold detection is performed on the influencing factors of abnormal operation of the cryogenic power grid. Based on preset thresholds, which modules or components exceed normal operating thresholds are identified and judged as potential fault sources. Data-driven methods (such as anomaly detection algorithms, machine learning models, etc.) are used to identify abnormal areas and generate fault source location data, indicating the area or equipment where the fault occurred. Based on the fault source location data, the fault sources are classified. Classification criteria may include equipment failure, line failure, load imbalance, environmental impact, etc. Classification algorithms (such as decision trees, support vector machines, etc.) are used to label the fault types and generate fault feature data. Based on the fault feature data, the severity of the fault is assessed. Assessment criteria include the impact range of the fault on the power grid, voltage deviation, power loss, etc. A weighted scoring model or multi-level analysis method is used to grade the fault, generating fault grade data to represent the severity of the fault. Fault source location data, fault type classification data, and fault grade data are generated for subsequent propagation path prediction and fault diffusion analysis. Connectivity analysis is performed on the structural topology data of the cryogenic power grid to assess the connection relationships between modules, especially the network connectivity of the area surrounding the fault source. Network connectivity data is generated using graph theory analysis methods (such as node degree, connectivity analysis, and shortest path algorithms) to indicate the connection strength and stability between different nodes in the power grid. Based on fault level data and network connectivity data, propagation path prediction is performed. Combining power grid topology, fault level, and influencing factors, the path of fault propagation from its source is predicted. Propagation models (such as information diffusion models and fault propagation simulations) are used to predict the fault propagation path, generating path prediction data. Propagation time-series analysis is performed on the path prediction data to assess the impact of the fault on the power grid at different time points. Emphasis is placed on the fault's expansion rate, impact time, and the delay of gradual transmission. Time-series analysis methods (such as time series analysis and dynamic models) are used to generate time-series characteristic data, indicating the temporal characteristics of the fault propagation process. Path prediction data and time-series characteristic data are generated to provide input for subsequent fault propagation simulation and spatiotemporal evolution analysis. Based on the time-series characteristic data, fault propagation simulation is performed on the propagation path prediction data to simulate the process of the fault spreading from its source to other parts of the power grid. Simulation models (such as dynamic system models and fluid propagation models) are used to simulate the fault propagation process and generate propagation process data, indicating the speed, scope, and impact of fault propagation. Spatiotemporal evolution analysis is performed on the propagation process data to observe the evolution patterns of the fault in spatial and temporal dimensions. The impact of fault propagation on the spatial distribution and temporal variations of the power grid is analyzed. Spatiotemporal data analysis methods (such as spatial statistical models and spatiotemporal matrices) are used to study the evolutionary laws of fault propagation and generate evolutionary pattern data. Using the evolutionary pattern data, the influence domain of abnormal modules in the low-temperature power grid is calculated, and the degree of impact of the fault propagation process on various modules and regions of the power grid is analyzed.The system calculates the number of affected areas, devices, and nodes in the power grid, as well as the severity of their faults, thereby generating power grid cascade power fault propagation data. This data includes propagation process data, spatiotemporal evolution analysis data, and power grid cascade power fault propagation data, which are used to assess the overall impact of fault propagation and guide power grid recovery strategies.

[0110] As an example of the present invention, reference is made to Figure 3 As shown, step S3 in this example includes:

[0111] Step S31: Divide the power grid cascade power fault propagation data into a dataset to generate a model training set and a model test machine; use the random forest algorithm to train the model on the training set to generate a pre-model for power grid cascade fault risk assessment.

[0112] Step S32: Optimize and iterate the pre-model for power grid cascade fault risk assessment using the model test set to generate a power grid cascade fault risk assessment model; import the power grid cascade power fault propagation data into the power grid cascade fault risk assessment model to predict power fault risks and generate power grid power fault risk prediction data.

[0113] Step S33: Label the fault risk level of the cascaded power fault propagation data of the power grid according to the power grid fault risk prediction data, and generate the cascaded power fault risk level of the power grid; use the power grid cascaded control optimization formula to optimize the cascaded power fault risk level of the power grid, and generate the cascaded operation optimization data of the power grid.

[0114] Step S34: Based on the power grid cascade operation optimization data, construct a power grid operation optimization scheme for the risk level of cascaded power faults, thereby generating a power grid cascaded fault operation optimization scheme.

[0115] In this embodiment of the invention, the data on the propagation of cascaded power grid faults is divided into a training set and a test set. Typically, 70%-80% of the data is used for the training set, and the remainder for the test set. During the partitioning, it is crucial to ensure the diversity and representativeness of the data so that the model can effectively learn the characteristics of power grid fault risk assessment. A random forest algorithm is used to train the model on the training set. The random forest algorithm generates an efficient prediction model by constructing multiple decision trees and combining their results. During training, the model learns the relationship between different fault propagation characteristics and power grid risk, and uses this information to generate a pre-model for assessing the risk of cascaded power grid faults. The pre-model is then validated and optimized using a test set. During this process, the model's performance is evaluated using metrics such as accuracy, recall, and F1 score. Based on the model's evaluation results, parameters are adjusted (e.g., adjusting the number of trees, depth, minimum number of splits, etc.) to achieve iterative optimization of the model. After multiple iterations, the model's predictive performance is significantly improved, ultimately generating a cascaded power grid fault risk assessment model. The data on the propagation of cascaded power grid faults is input into an optimized cascaded power grid fault risk assessment model for power fault risk prediction. Based on the input data, the model outputs fault risk assessment results for each module of the power grid and generates power grid fault risk prediction data, providing risk predictions for each module and a basis for subsequent risk management and optimization. Based on the power grid fault risk prediction data, the cascaded power grid fault propagation data is labeled with fault risk levels. Risk level labeling is based on preset standards, classifying fault risks into different levels (e.g., low risk, medium risk, high risk). The labeling process is typically based on the model output and combined with actual power grid operation standards. The cascaded power grid control optimization formula is used to optimize the cascaded operation of the cascaded power grid fault risk levels. The optimization formula comprehensively considers power grid dispatching, load allocation, and backup power resources under different risk levels, aiming to improve power grid operating efficiency and reduce the probability of fault occurrence. The goal of this step is to reduce the impact of risks in the system and enhance the robustness and fault tolerance of the power grid by optimizing the power grid dispatching strategy. Based on the cascaded operation optimization data, a power grid fault operation optimization scheme is constructed. This scheme considers optimized dispatch data, grid load, backup system configuration, and other dispatch strategies. Through simulation and optimization algorithms, it determines the emergency response strategy for each module in the event of a fault, ensuring the grid system can quickly recover and maintain power supply stability in the event of cascading faults. The optimized scheme is verified and adjusted to evaluate its applicability and effectiveness in a real-world environment. Verification can be conducted using historical fault data or simulation data. If necessary, a feedback mechanism is used to adjust and improve the optimized scheme to ensure the grid has better response strategies to future potential faults.

[0116] Preferably, the optimization formula for grid cascade control in step S33 is as follows:

[0117]

[0118] In the formula, Let w represent the target value for optimizing cascaded operation of the power grid, where N represents the total number of power grid nodes. i Let P be the importance weight coefficient of the i-th node. i,actual Let P be the actual power of the i-th node. i,max Let ΔP be the maximum allowable power of the i-th node. i This is represented as the power fluctuation at the i-th node. Let t represent the time derivative of the power change at the i-th node, t represent the power change time, α represent the weighting coefficient of the power fluctuation, and β represent the weighting coefficient of the power change rate.

[0119] This invention analyzes and integrates a power grid cascade control optimization formula, which integrates multiple key factors, including: node importance weight w. i By assigning weights, priority is given to nodes critical to grid operation, ensuring that important nodes are optimized first. Power utilization rate This reflects the ratio of a node's actual power to its capacity, preventing node overload or resource waste. Power fluctuation ΔP i Capture short-term power fluctuations to reduce the risk of failures caused by these fluctuations. Power change rate. By focusing on the rate of power change, sudden fluctuations in the power grid can be controlled. This is achieved by introducing the time derivative. The formula possesses dynamic optimization capabilities, enabling it to capture rapid changes in the power grid state in real time, adapt to complex operating environments, and improve the timeliness and accuracy of control. By comprehensively considering power fluctuations and their rates of change, the formula can provide early warnings of cascading faults and prioritize the resolution of high-risk nodes during optimization, significantly reducing the level of power grid fault risk. Optimization target value The calculation comprehensively considers power allocation and node importance weights to achieve optimal resource allocation and improve the overall operating efficiency of the power grid. The parameters in the formula (such as α, β, and weight w) iIt has adjustment range and can be flexibly adjusted according to different power grid operation needs, thus being suitable for power grid systems of various sizes and complexities. While conventional power grid cascade control optimization formulas in the field can yield the target value for power grid cascade operation optimization, the power grid cascade operation optimization formula provided by this invention can calculate the target value for power grid cascade operation optimization more accurately. This formula, by quantifying and optimizing multiple key indicators of power grid operation, can improve the operating efficiency and control flexibility of the power grid while ensuring safety and reliability, and is particularly suitable for the operation optimization tasks of complex cascaded power grids.

[0120] Preferably, step S4 includes the following steps:

[0121] Step S41: Collect operation feedback data based on the power grid cascade fault operation optimization scheme to obtain power grid cascade fault operation optimization feedback data; evaluate the operation optimization performance of the power grid cascade fault operation optimization feedback data to generate power grid operation optimization performance evaluation data;

[0122] Step S42: Update the power grid cascade fault operation optimization scheme using the power grid cascade fault operation optimization feedback data, and generate a power grid cascade fault operation optimization update scheme to execute the low temperature power grid operation optimization operation.

[0123] In this embodiment of the invention, after implementing the power grid cascade fault operation optimization scheme, the operation of the power grid is monitored in real time, and relevant feedback data is collected. This data includes power grid load changes, fault occurrence frequency, voltage stability, equipment status, and power transmission efficiency. Feedback data acquisition can be achieved through sensors installed at key nodes of the power grid, monitoring systems, and real-time data streams. The data should cover all aspects, including the actual operation of power generation, transmission, distribution, and user terminals. The collected operational feedback data is analyzed in detail to evaluate the effectiveness of the power grid operation optimization scheme. Key evaluation indicators include power grid fault recovery time, system reliability, resource utilization, energy loss, and operating costs. A performance evaluation model is used to compare the power grid operation performance before and after optimization, generating power grid operation optimization performance evaluation data. This evaluation data can include quantitative analysis results (such as fault response time, energy utilization, etc.) and qualitative feedback (such as user satisfaction, system stability, etc.), generating power grid operation optimization performance evaluation data to assess the effectiveness of the optimization scheme in actual operation and provide a basis for improving the optimization scheme. Based on performance evaluation data, the shortcomings of existing optimization schemes are analyzed, and necessary adjustments and optimizations are made. These adjustments include changing grid dispatching strategies, optimizing load allocation schemes, increasing the redundancy of key equipment, and adding fault recovery strategies. During the scheme update process, the special needs of low-temperature grids must be considered, especially in extreme low-temperature environments where grid equipment faces additional load pressure and fault risks. Therefore, scheme updates need to focus on system robustness, resilience, and adaptability. The updated grid cascade fault operation optimization scheme is applied to the actual operation of the low-temperature grid. This includes implementing new dispatching schemes, adjusting load allocation, and executing new fault emergency plans to improve the stability and reliability of the grid in low-temperature environments. During implementation, the grid's operating status is continuously monitored to ensure the effectiveness of the scheme. Necessary fine-tuning and real-time optimization are made based on actual operating conditions to generate updated grid cascade fault operation optimization schemes. Low-temperature grid operation optimization operations are then implemented to provide continuous optimization schemes for the long-term stable operation of the grid.

[0124] This specification provides a low-temperature power grid operation safety monitoring system based on intelligent algorithms, used to execute the aforementioned low-temperature power grid operation optimization method based on intelligent algorithms. The low-temperature power grid operation safety monitoring system based on intelligent algorithms includes:

[0125] The power grid modeling module is used to acquire low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; and perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of low-temperature power grid operation.

[0126] The cascaded fault analysis module is used to filter abnormal modules in the three-dimensional modeling data of low-temperature power grid operation based on preset abnormal index thresholds to obtain abnormal modules of low-temperature power grid operation; perform hierarchical abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal operation impact factors of low-temperature power grid operation; and perform cascaded fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal operation impact factors of low-temperature power grid operation to generate cascaded power fault diffusion data of the power grid.

[0127] The power grid operation optimization module is used to predict power fault risks from cascaded power fault propagation data and generate power grid power fault risk prediction data; to optimize the cascaded operation of the cascaded power fault propagation data based on the power grid power fault risk prediction data and generate cascaded operation optimization data; and to construct power grid operation optimization schemes based on the cascaded operation optimization data, thereby generating cascaded fault operation optimization schemes.

[0128] The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascade fault operation optimization scheme and generate power grid operation optimization performance evaluation data; it also uses the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

[0129] The beneficial effects of this invention lie in ensuring the systematic and hierarchical nature of the power grid by acquiring low-temperature power grid structure data and dividing the power grid into constituent modules. By collecting power grid operation data and performing 3D modeling, low-temperature power grid operation data is generated, improving the visualization and accuracy of power grid operation. This helps to comprehensively understand the power grid's operating status and potential problems, thus laying the foundation for subsequent optimization and fault analysis. By screening abnormal modules based on preset abnormal indicator thresholds, potential fault areas in the power grid can be identified in a timely manner, thereby avoiding the risk of grid-wide outages. Through hierarchical anomaly impact analysis and cascaded fault propagation analysis, this module effectively predicts and tracks fault propagation paths, accurately assesses the scope and degree of fault impact, and improves the accuracy of fault detection early warning and response strategies. Through the prediction of power fault risks and cascaded operation optimization, the risk of large-scale power grid failures is effectively reduced. By constructing power grid operation optimization schemes, the operation of the power grid can be dynamically adjusted, power grid resource allocation can be optimized, and the operating efficiency and stability of the power grid in low-temperature environments can be improved, providing a guarantee for the sustainability of power grid operation. Performance evaluation of the power grid operation optimization schemes can measure the effectiveness of the optimization schemes and provide a basis for subsequent scheme improvements. By updating the optimization scheme using feedback data, the power grid's efficient response capability under different operating environments and fault conditions is ensured. Through continuous optimization, the overall operating efficiency, fault response capability, and energy utilization rate of the power grid are improved. Therefore, this invention enhances the safety and intelligence of cryogenic power grid operation through intelligent modular analysis, fault propagation prediction and optimization, and a real-time feedback mechanism.

[0130] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0131] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for optimizing the operation of a low-temperature power grid based on intelligent algorithms, characterized in that, Includes the following steps: Step S1: Obtain low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; Based on the data of the power grid component modules, power grid operation data of the low-temperature power grid is collected to obtain standard low-temperature power grid operation data. Perform three-dimensional modeling of power grid operation on standard low-temperature power grid operation data to generate three-dimensional modeling data of low-temperature power grid operation; Step S2: Based on preset abnormal index thresholds, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation. A hierarchical abnormal operation impact analysis was conducted on the abnormal operation module of the low-temperature power grid to generate the abnormal operation impact factor of the low-temperature power grid. A cascaded fault propagation analysis of the low-temperature power grid operation anomaly module is performed using the low-temperature power grid operation anomaly influencing factors to generate power grid cascaded power fault propagation data; wherein, step S2 includes the following steps: Step S21: Based on the preset abnormal index threshold, perform power grid anomaly monitoring on the three-dimensional modeling data of low temperature power grid operation to obtain low temperature power grid anomaly monitoring data; Step S22: Based on the abnormal monitoring data of the low-temperature power grid, the abnormal modules of the three-dimensional modeling data of the low-temperature power grid operation are screened to obtain the abnormal modules of the low-temperature power grid operation; Step S23: Perform a hierarchical abnormal operation impact analysis on the low-temperature power grid operation anomaly module to generate low-temperature power grid operation anomaly impact factors; Step S24: Perform cascaded fault propagation analysis on the low-temperature power grid operation anomaly module using the low-temperature power grid operation anomaly influencing factors to generate power grid cascaded power fault propagation data; wherein, step S24 includes the following steps: Step S241: Detect thresholds for the influencing factors of abnormal operation of the low-temperature power grid to generate fault source location data; classify the fault source location data into fault types to generate fault feature data; assess the severity of the fault feature data to generate fault level data. Step S242: Perform connectivity analysis on the low-temperature power grid structure topology data to generate network connection data; perform propagation path prediction on the fault level data and network connection data to generate path prediction data; perform propagation time series analysis on the path prediction data to generate time series feature data. Step S243: Perform fault propagation simulation on the path prediction data based on the time series feature data to generate propagation process data; perform spatiotemporal evolution analysis on the propagation process data to generate evolution pattern data; use the evolution pattern data to calculate the influence domain of the low temperature power grid operation anomaly module to generate power grid cascaded power fault propagation data. Step S3: Perform power fault risk prediction on the cascaded power fault propagation data of the power grid to generate power grid power fault risk prediction data; perform cascade operation optimization on the cascaded power fault propagation data of the power grid based on the power grid power fault risk prediction data to generate power grid cascade operation optimization data; construct a power grid operation optimization scheme based on the power grid cascade operation optimization data to generate a power grid cascaded fault operation optimization scheme. Step S4: Based on the power grid cascade fault operation optimization scheme, conduct an operation optimization performance evaluation and generate power grid operation optimization performance evaluation data; use the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

2. The method for optimizing the operation of a low-temperature power grid based on intelligent algorithms according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain cryogenic power grid structure data; Step S12: Perform grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; divide the low-temperature grid structure data into grid component modules using the low-temperature grid structure topology data to generate grid component module data, wherein the grid component module division includes generation module, transmission module, distribution module and user power consumption module; Step S13: Collect power grid operation data from the low-temperature power grid based on the power grid component module data to obtain low-temperature power grid operation data; perform data preprocessing on the low-temperature power grid operation data to generate standard low-temperature power grid operation data, wherein data preprocessing includes data denoising, data filtering, data normalization and data standardization; Step S14: Perform three-dimensional modeling of the power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of the low-temperature power grid operation.

3. The method for optimizing the operation of a low-temperature power grid based on intelligent algorithms according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Extract key operating data from the standard low-temperature power grid operation data to obtain key operating data of the low-temperature power grid, which includes operating temperature data, voltage and current data and power load data. Step S142: Spatial positioning of power grid equipment is performed on the low-temperature power grid structure data to generate power grid equipment coordinate data; the path of the power grid equipment coordinate data is drawn to generate line route data; Step S143: Spatial modeling of the low-temperature power grid structure data is performed using line routing data to generate low-temperature power grid spatial site layout data; spatial site data is imported from the low-temperature power grid spatial site layout data based on operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

4. The method for optimizing the operation of a low-temperature power grid based on intelligent algorithms according to claim 1, characterized in that, Step S23 includes the following steps: Step S231: Collect basic power generation data from the power generation module in the low-temperature power grid operation anomaly module to obtain basic power generation module data; perform power generation cooling analysis on the basic power generation module data to generate power generation module cooling data; and perform first influencing factor transformation on the basic power generation module data based on the power generation module cooling data to generate power generation module influencing factors. Step S232: Collect basic transmission data for the transmission module in the low-temperature power grid operation anomaly module to obtain basic transmission module data; assess the line icing load status based on the basic transmission module data to generate transmission module line assessment data; analyze the insulation performance of the basic transmission module data using the transmission module line assessment data to generate transmission module insulation performance data; and perform a second influencing factor transformation on the basic generation module data based on the transmission module insulation performance data to generate transmission module influencing factors. Step S233: Collect basic transmission data for the distribution module in the low-temperature power grid operation anomaly module to obtain basic distribution module data; perform power grid cooling efficiency analysis on the basic distribution module data to generate distribution cooling efficiency data; perform third influencing factor transformation on the basic distribution module data based on the distribution cooling efficiency data to generate distribution module influencing factors; Step S234: Collect basic power consumption data from the user power consumption modules in the low-temperature power grid operation anomaly module to obtain basic power consumption module data; perform power grid load characteristic analysis on the basic power consumption module data to generate power load characteristic data; and perform fourth influencing factor transformation on the basic power consumption module data based on the power load characteristic data to generate power consumption module influencing factors. Step S235: Integrate the influence factors of the power generation module, the power transmission module, the power distribution module, and the power consumption module to generate the low-temperature power grid operation anomaly influence factor.

5. The method for optimizing the operation of a low-temperature power grid based on intelligent algorithms according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Divide the power grid cascade power fault propagation data into a dataset to generate a model training set and a model test machine; use the random forest algorithm to train the model on the training set to generate a pre-model for power grid cascade fault risk assessment. Step S32: Optimize and iterate the pre-model for power grid cascade fault risk assessment using the model test set to generate a power grid cascade fault risk assessment model; import the power grid cascade power fault propagation data into the power grid cascade fault risk assessment model to predict power fault risks and generate power grid power fault risk prediction data. Step S33: Label the fault risk level of the cascaded power fault propagation data of the power grid according to the power grid fault risk prediction data, and generate the cascaded power fault risk level of the power grid; use the power grid cascaded control optimization formula to optimize the cascaded power fault risk level of the power grid, and generate the cascaded operation optimization data of the power grid. Step S34: Based on the power grid cascade operation optimization data, construct a power grid operation optimization scheme for the risk level of cascaded power faults, thereby generating a power grid cascaded fault operation optimization scheme.

6. The method for optimizing the operation of a cryogenic power grid based on intelligent algorithms according to claim 5, characterized in that, The optimization formula for power grid cascade control in step S33 is as follows: In the formula, This represents the target value for optimizing cascaded power grid operation. Represented as the total number of power grid nodes, Represented as the first The importance weight coefficient of each node Represented as the first The actual power of each node Represented as the first Maximum allowable power of each node Represented as the first Power fluctuation at each node Represented as the first Time derivative of the power change at each node This is expressed as the time of power change. This is expressed as a weighting coefficient for power fluctuation. It is represented as a weighting coefficient for the rate of power change.

7. The method for optimizing the operation of a low-temperature power grid based on intelligent algorithms according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Collect operation feedback data based on the power grid cascade fault operation optimization scheme to obtain power grid cascade fault operation optimization feedback data; evaluate the operation optimization performance of the power grid cascade fault operation optimization feedback data to generate power grid operation optimization performance evaluation data; Step S42: Update the power grid cascade fault operation optimization scheme using the power grid cascade fault operation optimization feedback data, and generate a power grid cascade fault operation optimization update scheme to execute the low temperature power grid operation optimization operation.

8. A low-temperature power grid operation safety monitoring system based on intelligent algorithms, characterized in that, For executing the intelligent algorithm-based low-temperature power grid operation optimization method as described in claim 1, the intelligent algorithm-based low-temperature power grid operation safety monitoring system includes: The power grid modeling module is used to acquire low-temperature power grid structure data; divide the low-temperature power grid structure data into power grid component modules to generate power grid component module data; collect power grid operation data based on the power grid component module data to obtain standard low-temperature power grid operation data; and perform three-dimensional modeling of power grid operation based on the standard low-temperature power grid operation data to generate three-dimensional modeling data of low-temperature power grid operation. The cascaded fault analysis module is used to filter abnormal modules in the three-dimensional modeling data of low-temperature power grid operation based on preset abnormal index thresholds to obtain abnormal modules of low-temperature power grid operation; perform hierarchical abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal operation impact factors of low-temperature power grid operation; and perform cascaded fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal operation impact factors of low-temperature power grid operation to generate cascaded power fault diffusion data of the power grid. The power grid operation optimization module is used to predict power fault risks from cascaded power fault propagation data and generate power grid power fault risk prediction data; to optimize the cascaded operation of the cascaded power fault propagation data based on the power grid power fault risk prediction data and generate cascaded operation optimization data; and to construct power grid operation optimization schemes based on the cascaded operation optimization data, thereby generating cascaded fault operation optimization schemes. The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascade fault operation optimization scheme and generate power grid operation optimization performance evaluation data; it also uses the power grid cascade fault operation optimization feedback data to update the power grid cascade fault operation optimization scheme and generate a power grid cascade fault operation optimization update scheme to execute low temperature power grid operation optimization operations.

Images