Low-temperature power grid operation optimization method based on intelligent algorithm and safety monitoring system

Abstract

The invention relates to the technical field of power grid operation optimization, in particular to a low-temperature power grid operation optimization method based on an intelligent algorithm and a safety monitoring system. The method comprises the following steps: acquiring low-temperature power grid structure data; performing power grid composition module division on the low-temperature power grid structure data to generate power grid composition module data; performing power grid operation data acquisition on the low-temperature power grid based on the power grid composition module data to obtain standard low-temperature power grid operation acquisition data; performing power grid operation three-dimensional modeling on the standard low-temperature power grid operation acquisition data to generate low-temperature power grid operation three-dimensional modeling data; and performing abnormal module screening on the low-temperature power grid operation three-dimensional modeling data based on a preset abnormal index threshold to obtain a low-temperature power grid operation abnormal module. According to the invention, through intelligent modular analysis, fault diffusion prediction and optimization and a real-time feedback mechanism, the operation safety and intelligence of the low-temperature power grid are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid operation optimization, and in particular to a low-temperature power grid operation optimization method and a safety monitoring system based on an intelligent algorithm. Background Art

[0002] Early low-temperature power grid optimization methods mainly rely on traditional engineering technology and empirical rules, but these methods often lack flexibility and adaptability. With the development of computer technology and data analysis capabilities, especially the rise of big data and artificial intelligence (AI) technology, intelligent algorithms have gradually become the core tools for power grid optimization. Power grid optimization methods based on intelligent algorithms can accurately predict the load changes, equipment operating status and possible failure risks of power grids under low temperatures through real-time data collection and processing. In recent years, intelligent algorithms such as deep learning, genetic algorithms, and particle swarm optimization (PSO) have been widely used in power grid operation optimization. For example, deep learning can train models with historical data to achieve accurate prediction and dynamic scheduling of power grid loads; particle swarm optimization can be used to optimize the operation strategies of each node 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 have good adaptability and real-time performance. However, at present, traditional power grid fault detection often finds it difficult to handle sudden faults and complex fault propagation processes caused by low temperatures. At the same time, there is a lack of intelligent optimization in the emergency handling of power grid operation faults, which leads to low safety and intelligence of power grid operation. Summary of the invention

[0003] Based on this, it is necessary to provide a low-temperature power grid operation optimization method and a safety monitoring system based on an intelligent algorithm to solve at least one of the above technical problems.

[0004] To achieve the above object, a low temperature power grid operation optimization method based on an intelligent algorithm is provided, the method comprising the following steps:

[0005] Step S1: 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data;

[0006] Step S2: Based on the preset abnormal index threshold, the abnormal module of the low-temperature power grid operation three-dimensional modeling data is screened to obtain the abnormal module of the low-temperature power grid operation; the layered abnormal operation impact analysis is performed on the abnormal module of the low-temperature power grid operation to generate the abnormal impact factor of the low-temperature power grid operation; the cascade fault diffusion analysis is performed on the abnormal module of the low-temperature power grid operation through the abnormal impact factor of the low-temperature power grid operation to generate the cascade power fault diffusion data of the power grid;

[0007] Step S3: performing power failure risk prediction on the power grid cascade power failure diffusion data to generate power grid power failure risk prediction data; performing cascade operation optimization on the power grid cascade power failure diffusion data according to the power grid power failure risk prediction data to generate power grid cascade operation optimization data; constructing a power grid operation optimization plan based on the power grid cascade operation optimization data to generate a power grid cascade failure operation optimization plan;

[0008] Step S4: Perform an operation optimization performance evaluation based on the power grid cascading fault operation optimization plan to generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan to generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

[0009] The present invention can comprehensively and meticulously understand the composition, operation status and structural characteristics of the power grid by modularizing and three-dimensionally modeling the low-temperature power grid structure data. It provides accurate basic data for subsequent data collection, fault analysis and optimization, ensures the true reflection of the power grid operation status, and helps further optimization work. Based on the preset abnormal index threshold, the abnormal module is screened, and the potential fault source in the operation of the low-temperature power grid can be accurately identified. Through hierarchical analysis and cascade fault diffusion, the fault propagation path and the impact range can be revealed, and the possible risk area of ​​the power grid can be predicted in advance, thereby providing an accurate basis for subsequent fault prediction and optimization to prevent large-scale power outages. Through power fault risk prediction, the high-risk areas faced by the power grid under low temperature conditions can be identified in advance and dynamically adjusted. Through cascade operation optimization, the spread of faults can be effectively avoided or reduced, the fault tolerance and stability of the power grid can be improved, the smooth operation of the power grid in a complex environment can be guaranteed, and large-scale power outages can be avoided. By performing performance evaluation on the optimization scheme, the effect of the optimization scheme can be quantified to ensure the feasibility and effectiveness of the operation optimization scheme. Using optimized feedback data to update the scheme can dynamically adapt to changes in the actual operation of the power grid, ensure that the power grid always maintains the best operating state in a low-temperature environment, and improve the flexibility of the system and its ability to respond to emergencies. Therefore, the present invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault diffusion prediction and optimization, and real-time feedback mechanism.

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

[0011] Step S11: obtaining low temperature power grid structure data;

[0012] Step S12: performing a grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; dividing 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 a power generation module, a power transmission module, a power distribution module, and a user power module;

[0013] Step S13: collecting grid operation data of the low-temperature grid based on the grid component module data to obtain low-temperature grid operation collection data; performing data preprocessing on the low-temperature grid operation collection data to generate standard low-temperature grid operation collection data, wherein the data preprocessing includes data denoising, data filtering, data normalization and data standardization;

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

[0015] The present invention can fully grasp the overall structure and detailed characteristics of the low-temperature power grid by acquiring the low-temperature power grid structure data and performing topological analysis and module division, and divide it into power generation, transmission, distribution and user power modules, so that the composition of the power grid system is clearer, which is convenient for subsequent targeted analysis and optimization. The collection and preprocessing of the low-temperature power grid operation data ensure the accuracy, integrity and consistency of the data. Data denoising, filtering, normalization and standardization and other processing methods significantly improve the data quality, providing a reliable basis for subsequent analysis and modeling. Based on the standardized operation data, a three-dimensional model of the low-temperature power grid is generated, which can intuitively display the operation status of the power grid, facilitate engineers to observe and analyze key operating parameters, and this visualization method helps to quickly find problems and formulate optimization measures. The division of power generation, transmission, distribution and user power modules helps to decompose the complex power grid system into parts that are easy to manage and optimize. The data collection and analysis of each module can be carried out in parallel to improve the overall efficiency. Through the modeling and visualization analysis of the low-temperature power grid operation data, potential problems such as power loss, abnormal operation, etc. can be found, and the operation strategy can be optimized in a targeted manner, thereby improving the operation efficiency and reliability of the power grid. All steps are closely linked, and the generated 3D modeling data is not only the basis for operation monitoring, but also provides data support and model basis for subsequent simulation, optimized scheduling and intelligent control.

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

[0017] Step S141: extracting key operation data from the standard low-temperature power grid operation collection data to obtain key operation data of the low-temperature power grid, wherein the key operation data of the low-temperature power grid includes operation temperature data, voltage and current data, and power load data;

[0018] Step S142: spatially locate the power grid equipment on the low-temperature power grid structure data to generate power grid equipment coordinate data; and path-delineate the power grid equipment coordinate data to generate line direction data;

[0019] Step S143: spatially model the low-temperature power grid structure data through line direction data to generate low-temperature power grid spatial site layout data; import spatial site data into the low-temperature power grid spatial site layout data according to operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

[0020] The present invention accurately captures the core operating indicators of the low-temperature power grid by extracting key operating data (such as operating temperature, voltage and current, power load, etc.), highlighting the focus of data analysis. The extracted key data directly reflects the operating status of the power grid, providing a reliable basis for subsequent modeling and optimization. The spatial positioning and coordinate generation of power grid equipment closely integrate the physical structure of the power grid with the operating data, which is convenient for locating the distribution of equipment in the power grid. The line direction data generated by path description clearly shows the power transmission path of the power grid, which is convenient for analyzing the flow of electric energy and identifying potential bottlenecks or abnormal points. Spatial modeling converts the physical structure of the low-temperature power grid into intuitive three-dimensional layout data, enhances the visualization effect of the system, and enables engineers to clearly understand the power grid structure and site distribution. Key data such as operating temperature, voltage and current, and power load are imported into the spatial site layout to further enrich the practicality of three-dimensional modeling and provide a more realistic and dynamic operating model. The three-dimensional modeling data integrates the spatial structure of the power grid with the operating data, realizing multi-dimensional monitoring of power grid operation. Engineers can quickly detect equipment anomalies, line failures and other problems through the model, improving the efficiency of problem troubleshooting. The generation of a 3D model is not only a visualization of the static structure, but also provides data support for subsequent simulation, dynamic optimization scheduling and load distribution, helping to improve the overall operation efficiency and stability of the power grid. The clear decomposition of steps facilitates different teams to handle operation data extraction, equipment positioning, path description and 3D modeling in parallel, improving the efficiency of project implementation. The generated 3D modeling data can be used as a basic module for subsequent data analysis, prediction and optimization, supporting further expansion and application.

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

[0022] Step S21: performing grid anomaly monitoring on the low-temperature grid operation three-dimensional modeling data based on a preset abnormal index threshold to obtain low-temperature grid abnormal monitoring data;

[0023] Step S22: screening abnormal modules of the low-temperature power grid operation three-dimensional modeling data according to the low-temperature power grid abnormal monitoring data to obtain the low-temperature power grid operation abnormal module;

[0024] Step S23: performing hierarchical abnormal operation impact analysis on the low-temperature power grid operation abnormality module to generate a low-temperature power grid operation abnormality impact factor;

[0025] Step S24: performing cascading fault diffusion analysis on the low-temperature power grid operation abnormality module according to the low-temperature power grid operation abnormality influencing factors, and generating power grid cascading power fault diffusion data.

[0026] The present invention can quickly detect abnormal phenomena in the operation of the power grid, such as excessive temperature, abnormal voltage or load imbalance, by monitoring the three-dimensional modeling data of the low-temperature power grid operation based on a preset abnormal index threshold. Automated monitoring reduces the need for manual intervention, improves the efficiency of abnormal detection, and can issue early warnings in a timely manner. According to the abnormal monitoring data, the abnormal module of the three-dimensional modeling data of the power grid is screened, and the specific affected modules (such as power generation modules, transmission modules, etc.) are clarified, so as to accurately locate the problem to a specific area or device. The screened abnormal modules enable subsequent analysis to be targeted and avoid data redundancy and resource waste. The hierarchical impact analysis of the abnormal modules can reveal the specific impact of the abnormalities on the operation of the power grid from multiple dimensions (such as the equipment layer, the line layer, and the system layer), and the generated abnormal impact factors provide quantitative reference indicators, laying the foundation for subsequent optimization and repair work. Through the abnormal impact factors, cascading fault diffusion analysis can be performed, how the impact of the abnormal modules is propagated in the power grid can be simulated, and cascading power fault diffusion data can be generated. This analysis method can predict potential systemic risks in advance and avoid large-scale power outages or system crashes due to single point failures. The entire chain of steps ensures full coverage of the process from abnormal monitoring to fault diffusion analysis, effectively improving the safety and stability of power grid operation. Through early detection and prediction of diffusion paths, operators can formulate targeted fault isolation or repair strategies to prevent problems from expanding. The generated low-temperature power grid abnormal monitoring data, abnormal influencing factors and fault diffusion data provide data support for the intelligent operation optimization of the power grid, and help develop more efficient scheduling algorithms and fault handling solutions.

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

[0028] Step S231: collecting basic power generation data of the power generation module in the low-temperature power grid operation abnormality module to obtain basic data of the power generation module; performing power generation cooling analysis on the basic data of the power generation module to generate cooling data of the power generation module; performing a first influencing factor conversion on the basic data of the power generation module based on the cooling data of the power generation module to generate an influencing factor of the power generation module;

[0029] Step S232: collecting basic transmission data of the transmission module in the low-temperature power grid operation abnormality module to obtain basic data of the transmission module; evaluating the line icing load state of the basic data of the transmission module to generate line evaluation data of the transmission module; performing insulation performance analysis on the basic data of the transmission module using the line evaluation data of the transmission module to generate insulation performance data of the transmission module; performing a second influencing factor conversion on the basic data of the power generation module based on the insulation performance data of the transmission module to generate an influencing factor of the transmission module;

[0030] Step S233: collecting basic data of power transmission from the power distribution module in the low-temperature power grid operation abnormality module to obtain basic data of the power distribution module; performing power grid cooling efficiency analysis on the basic data of the power distribution module to generate power distribution cooling efficiency data; performing a third influencing factor conversion on the basic data of the power distribution module based on the power distribution cooling efficiency data to generate an influencing factor of the power distribution module;

[0031] Step S234: collecting basic power consumption data of the user power consumption module in the low-temperature power grid operation abnormality module to obtain basic power consumption module data; performing power grid load characteristic analysis on the basic power consumption module data to generate power consumption load characteristic data; performing a fourth influencing factor conversion on the basic power consumption module data based on the power consumption load characteristic data to generate a power consumption module influencing factor;

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

[0033] The present invention can ensure that the key operating status of abnormal modules is fully recorded by collecting independent basic data for power generation, transmission, distribution and user power modules. The strategy of sub-module collection effectively avoids data omissions and provides detailed and accurate data support for subsequent analysis. Cooling data reveals the operating efficiency and temperature control capability of the power generation module in a low temperature environment, helping to identify the key factors affecting the power generation efficiency. The converted influencing factors quantify the impact of cooling on the performance of the power generation module, providing a reference for subsequent optimization. Ice load evaluation and insulation performance analysis can identify the reliability problems of transmission lines in extreme low temperature environments. The converted transmission module influencing factors quantify the specific impact of low temperature on line transmission performance and support line optimization design. Cooling efficiency analysis reveals the heat dissipation efficiency and operating stability of the distribution module in a low temperature environment. The converted influencing factors reflect the potential impact of cooling performance on power distribution, which helps to optimize the distribution design. Load characteristic analysis deeply explores the power consumption behavior and power demand characteristics of the user end in a low temperature environment. The converted influencing factors provide quantitative indicators of the user end operating status, which helps to reasonably allocate power grid resources. The influencing factors of the power generation module, transmission module, distribution module and user power module are integrated to generate the influencing factors of abnormal operation of low-temperature power grid, which fully reflects the overall characteristics of abnormal operation of power grid. The integration of influencing factors helps to evaluate the multi-faceted impact of low-temperature environment on the power grid from a global perspective and provide a scientific basis for the formulation of optimization strategies. Through modular collection, step-by-step analysis and integration of factors, the source and diffusion path of the anomaly are systematically analyzed. Accurately identifying the main influencing factors of the anomaly provides a direction for precise intervention in power grid management.

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

[0035] Step S241: performing threshold detection on the factors affecting the abnormal operation of the low-temperature power grid to generate fault source location data; classifying the fault type of the fault source location data to generate fault feature data; evaluating the severity of the fault feature data to generate fault level data;

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

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

[0038] The present invention accurately identifies the starting position of the fault and generates fault source location data by performing threshold detection on the influencing factors of abnormal operation of the low-temperature power grid. The fault source location data is used to classify the fault type and generate detailed fault feature data (such as short circuit, overload or line break). Combined with the fault feature data, the impact of the fault on the overall power grid is evaluated, and graded fault level data (such as slight, medium, and severe) is generated. Connectivity analysis is performed on the topological data of the low-temperature power grid structure, network connection data is generated, and the path of fault propagation is clarified. Combined with the fault level data and the network connection data, the path of fault propagation is predicted, and path prediction data is generated. Dynamic analysis is performed on the path prediction data to generate time series feature data including the fault propagation speed and time series features. Accurately predict the affected areas and paths based on the power grid topology structure and fault level data. Provide support for the formulation of dynamic response plans to reduce the secondary impact of fault propagation. Predict the diffusion range and duration in advance through time series feature data to support the early deployment of prevention and control measures. Reveal the potential fault propagation law through spatiotemporal evolution, and provide a basis for subsequent optimization design and prevention and control. Based on the impact domain calculation, quantify the actual impact of the fault on different modules or regions, and support precise decision-making.

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

[0040] Step S31: dividing the data set of the power grid cascade power fault diffusion data to generate a model training set and a model test set; using a random forest algorithm to perform model training on the model training set to generate a power grid cascade fault risk assessment pre-model;

[0041] Step S32: optimizing and iterating the pre-model of the power grid cascading failure risk assessment through the model test set, thereby generating a power grid cascading failure risk assessment model; importing the power grid cascading power failure diffusion data into the power grid cascading failure risk assessment model to perform power failure risk prediction, thereby generating power grid power failure risk prediction data;

[0042] Step S33: marking the grid cascade power fault diffusion data with fault risk levels according to the grid power fault risk prediction data to generate the grid cascade power fault risk level; performing cascade operation optimization on the grid cascade power fault risk level using the grid cascade control optimization formula to generate grid cascade operation optimization data;

[0043] Step S34: constructing a power grid operation optimization plan for the cascade power failure risk level based on the power grid cascade operation optimization data, thereby generating a power grid cascade failure operation optimization plan.

[0044] The present invention ensures the independence of model training and testing and improves the generalization ability of the model through reasonable data division. The random forest algorithm has strong processing ability for multidimensional data, ensuring that the generated pre-model has high accuracy and robustness. The optimization iterative process enables the model to adapt to different power grid operation scenarios and data characteristics. The predicted data provides a reliable basis for subsequent risk management and fault prevention. Based on the risk level labeled data, the power grid operation is optimized in a targeted manner to improve resource utilization efficiency. The risk, safety and cost are balanced through the control formula to ensure the reliability and economy of power grid operation. The optimization scheme comprehensively considers the power grid operation efficiency, fault prevention and control and recovery speed. The scheme construction uses the deep mining of optimization data to provide a reliable operation strategy for the smart grid. Through a data-driven method, a high-precision evaluation model is constructed to achieve efficient prediction and classification of power failure risks. Comprehensively considering the risk level, control cost and safety, an optimization scheme is formulated to improve the stability and reliability of power grid operation. Combined with risk prediction and optimization schemes, the power grid can take preventive measures before a fault occurs to reduce the scope and loss of the accident. Using machine learning technology and optimization algorithms, the power grid operation is promoted to move towards intelligence and improve the overall operation and maintenance level. The comprehensive optimization process takes into account both operational safety and economy, and builds a low-cost, high-yield power grid management system.

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

[0046]

[0047] In the formula, is the optimization target value of the power grid cascade operation, N is the total number of power grid nodes, and w i Expressed as the importance weight coefficient of the i-th node, P i,actual Expressed as the actual power of the i-th node, P i,max Denotes the maximum allowable power of the ith node, ΔP i Expressed as the power fluctuation of the i-th node, It is represented as the time derivative of the power change of the ith node, t is represented as the power change time, ɑ is represented as the weight coefficient of the power fluctuation, and β is represented as the weight coefficient of the power change rate.

[0048] The present invention analyzes and integrates a grid cascade control optimization formula, which integrates multiple key factors, including: node importance weight w i By assigning weights, we focus on nodes that are critical to the operation of the power grid and ensure that important nodes are optimized first. Reflects the ratio of the actual power of the node to its capacity, avoiding node overload or resource waste. Power fluctuation ΔP iCapture short-term power fluctuations and reduce the risk of failure caused by fluctuations. By focusing on the rate of power change, the sudden fluctuation problem in the power grid can be controlled. The formula has dynamic optimization capabilities, can capture rapid changes in grid status in real time, adapt to complex operating environments, and improve the timeliness and accuracy of regulation. By comprehensively considering the power fluctuation amount and change rate, the formula can provide early warning of cascading failures, and prioritize high-risk nodes during optimization, significantly reducing the risk level of grid failures. Optimization target value The calculation of takes into account the power allocation and node importance weights, thereby achieving the optimal allocation of resources and improving the overall operation efficiency of the power grid. The parameters in the formula (such as α, β and weight w i ) has adjustment space and can be flexibly adjusted according to different grid operation requirements, so it is suitable for grid systems of various sizes and complexities. When using the conventional grid cascade control optimization formula in this field, the grid cascade operation optimization target value can be obtained. By applying the grid cascade control optimization formula provided by the present invention, the grid cascade operation optimization target value can be calculated more accurately. This formula can improve the operation efficiency and control flexibility of the grid while ensuring safety and reliability by quantifying and optimizing multiple key indicators of grid operation, and is particularly suitable for operation optimization tasks of complex cascade grids.

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

[0050] Step S41: collecting operation feedback data based on the power grid cascading fault operation optimization scheme to obtain power grid cascading fault operation optimization feedback data; performing operation optimization performance evaluation on the power grid cascading fault operation optimization feedback data to generate power grid operation optimization performance evaluation data;

[0051] Step S42: using the grid cascading fault operation optimization feedback data to update the grid cascading fault operation optimization scheme, generating a grid cascading fault operation optimization update scheme to perform low-temperature grid operation optimization operations.

[0052] The present invention forms a closed-loop process for power grid operation optimization through the operation feedback data collection and performance evaluation of step S41. This feedback mechanism can timely capture potential problems in power grid operation, evaluate the actual effect of the optimization scheme, and ensure the reliability and continuous improvement of the optimization scheme. The collection of operation feedback data and performance evaluation provide high-quality basic data for the update of the optimization scheme. Using these data, step S42 can dynamically adjust the optimization strategy to make the optimization scheme more in line with actual operation requirements and enhance the adaptability of the power grid to variable operating environments (such as low temperature environments). By continuously updating the power grid cascading failure operation optimization scheme, potential cascading failure risks can be effectively identified and alleviated. Especially under low temperature operating conditions, this step can adjust the scheme according to feedback to ensure power grid stability and reduce the probability of failure caused by extreme environments. The synergy of optimization performance evaluation (S41) and scheme update (S42) helps to discover efficiency bottlenecks in operation and solve them through scheme adjustment, thereby achieving the optimal configuration of power grid resources and improving overall operating efficiency. Through the special design for low-temperature grid operation optimization, step S42 can be adjusted according to the grid characteristics (such as load fluctuations, increased cable losses, etc.) in a low-temperature environment to ensure that the grid can still operate safely and efficiently in extreme climates. This step combines feedback data with optimization performance evaluation to achieve an automated solution update process, introduces an intelligent decision-making mechanism for grid operation, and improves the automation and intelligence level of operation and control.

[0053] In this specification, a low-temperature power grid operation safety monitoring system based on an intelligent algorithm is provided, which is used to execute the low-temperature power grid operation optimization method of the above-mentioned intelligent algorithm. The low-temperature power grid operation safety monitoring system based on the intelligent algorithm includes:

[0054] The power grid modeling module is used to obtain the 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data;

[0055] The cascading fault analysis module is used to screen abnormal modules of the three-dimensional modeling data of low-temperature power grid operation based on the preset abnormal index threshold to obtain abnormal modules of low-temperature power grid operation; perform layered abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal impact factors of low-temperature power grid operation; perform cascading fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal impact factors of low-temperature power grid operation to generate grid cascading power fault diffusion data;

[0056] The power grid operation optimization module is used to predict the power grid cascade power fault diffusion data for power grid and generate power grid power fault risk prediction data; perform cascade operation optimization on the power grid cascade power fault diffusion data according to the power grid power fault risk prediction data and generate power grid cascade operation optimization data; construct a power grid operation optimization plan based on the power grid cascade operation optimization data, thereby generating a power grid cascade fault operation optimization plan;

[0057] The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascading fault operation optimization plan and generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan and generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

[0058] The beneficial effect of the present invention is that by acquiring the low-temperature power grid structure data and dividing the power grid component modules, the systematicness and hierarchy of the power grid are ensured. By collecting the power grid operation data and performing three-dimensional modeling, the operation data of the low-temperature power grid is generated, the visualization and accuracy of the power grid operation are improved, which is helpful to fully understand the operation status and potential problems of the power grid, thereby laying the foundation for subsequent optimization and fault analysis. By screening the abnormal module based on the preset abnormal index threshold, the potential fault area in the power grid can be identified in time, thereby avoiding the risk of outage across the entire network. Through hierarchical abnormal impact analysis and cascade fault diffusion analysis, the module effectively predicts and tracks the path of fault propagation, can accurately assess the scope and degree of fault impact, and improves the early warning of fault detection and the accuracy of the response strategy. By predicting the risk of power failure and optimizing the cascade operation, the risk of large-scale failures in the power grid is effectively reduced. By constructing a power grid operation optimization scheme, the operation of the power grid can be dynamically adjusted, the power grid resource configuration can be optimized, the operation efficiency and stability of the power grid in a low-temperature environment can be improved, and the sustainability of the power grid operation can be guaranteed. By evaluating the performance of the power grid operation optimization scheme, the effectiveness of the optimization scheme can be measured, providing a basis for subsequent scheme improvements. The optimization scheme is updated using feedback data to ensure the efficient response capability of the power grid in different operating environments and fault conditions. Through continuous optimization, the overall operating efficiency, fault response capability and energy utilization of the power grid are improved. Therefore, the present invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault diffusion prediction and optimization, and real-time feedback mechanism. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic flow chart of the steps of a low-temperature power grid operation optimization method based on an intelligent algorithm;

[0060] Figure 2 for Figure 1Detailed implementation steps of step S2 in the flowchart;

[0061] Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG.

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

[0063] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0064] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks 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 only 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, and the term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0066] To achieve this, please refer to Figures 1 to 3 , a low temperature power grid operation optimization method based on intelligent algorithm, the method comprising the following steps:

[0067] Step S1: 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data;

[0068] Step S2: Based on the preset abnormal index threshold, the abnormal module of the low-temperature power grid operation three-dimensional modeling data is screened to obtain the abnormal module of the low-temperature power grid operation; the layered abnormal operation impact analysis is performed on the abnormal module of the low-temperature power grid operation to generate the abnormal impact factor of the low-temperature power grid operation; the cascade fault diffusion analysis is performed on the abnormal module of the low-temperature power grid operation through the abnormal impact factor of the low-temperature power grid operation to generate the cascade power fault diffusion data of the power grid;

[0069] Step S3: performing power failure risk prediction on the power grid cascade power failure diffusion data to generate power grid power failure risk prediction data; performing cascade operation optimization on the power grid cascade power failure diffusion data according to the power grid power failure risk prediction data to generate power grid cascade operation optimization data; constructing a power grid operation optimization plan based on the power grid cascade operation optimization data to generate a power grid cascade failure operation optimization plan;

[0070] Step S4: Perform an operation optimization performance evaluation based on the power grid cascading fault operation optimization plan to generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan to generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

[0071] The present invention can comprehensively and meticulously understand the composition, operation status and structural characteristics of the power grid by modularizing and three-dimensionally modeling the low-temperature power grid structure data. It provides accurate basic data for subsequent data collection, fault analysis and optimization, ensures the true reflection of the power grid operation status, and helps further optimization work. Based on the preset abnormal index threshold, the abnormal module is screened, and the potential fault source in the operation of the low-temperature power grid can be accurately identified. Through hierarchical analysis and cascade fault diffusion, the fault propagation path and the impact range can be revealed, and the possible risk area of ​​the power grid can be predicted in advance, thereby providing an accurate basis for subsequent fault prediction and optimization to prevent large-scale power outages. Through power fault risk prediction, the high-risk areas faced by the power grid under low temperature conditions can be identified in advance and dynamically adjusted. Through cascade operation optimization, the spread of faults can be effectively avoided or reduced, the fault tolerance and stability of the power grid can be improved, the smooth operation of the power grid in a complex environment can be guaranteed, and large-scale power outages can be avoided. By performing performance evaluation on the optimization scheme, the effect of the optimization scheme can be quantified to ensure the feasibility and effectiveness of the operation optimization scheme. Using optimized feedback data to update the scheme can dynamically adapt to changes in the actual operation of the power grid, ensure that the power grid always maintains the best operating state in a low-temperature environment, and improve the flexibility of the system and its ability to respond to emergencies. Therefore, the present invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault diffusion prediction and optimization, and real-time feedback mechanism.

[0072] In the embodiment of the present invention, reference Figure 1 FIG. 1 is a schematic diagram of a step flow chart of a low-temperature power grid operation optimization method based on an intelligent algorithm of the present invention. In this example, the low-temperature power grid operation optimization method based on an intelligent algorithm includes the following steps:

[0073] Step S1: 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data;

[0074] In an embodiment of the present invention, real-time data is collected by sensors (such as temperature sensors, current sensors, voltage sensors, etc.) deployed in the low-temperature power grid. These sensors can provide operating status data of various parts of the power grid, such as equipment load, temperature, humidity, current, etc. The geographical location data of the power grid equipment (including power transformers, transmission lines, switchgear, etc.) are collected, and these location data are obtained through GPS positioning, map data or through a known power grid geographic information system (GIS). Based on power grid design drawings, geographic information systems (GIS), construction documents, etc., the basic topological structure of the power grid, such as nodes and connection relationships of substations, transmission lines, access equipment, distribution networks, etc., is obtained. The data from sensors, equipment locations and topological structures are integrated to form a complete low-temperature power grid structure data set. Ensure that the data collected from each sensor and device has a unified timestamp to facilitate subsequent data processing and analysis. According to the functions of different devices in the power grid (such as transmission, transformation, distribution, etc.), the power grid is divided into multiple functional modules, such as: substation module, transmission module, distribution module, etc. The power grid is divided into multiple regional modules according to geographical regions or power grid operation areas. Each regional module includes all power grid equipment and connections in the region. Divide the modules by equipment type (such as switchgear, transformer, battery energy storage device, etc.) to ensure that each module contains associated equipment and communication units. After the modules are divided, assign a unique identifier to each module and provide detailed parameters (such as voltage level, load capacity, transmission capacity, etc.) for the equipment and connections in each module. Record the connection relationship between different modules (for example, the current flow and power supply capacity between the substation module and the distribution module), and define clear input / output interfaces for each module. Integrate the data structure after the module division to generate a set of power grid component module data, which can be used for subsequent power grid operation monitoring, data analysis and optimization. Arrange sensors in each power grid module to monitor the operating status of each module in real time. Including current, voltage, temperature, equipment operating status, fault diagnosis data, etc. According to the real-time requirements of the power grid, set the data collection frequency (such as once every minute or every hour) to ensure that sufficiently detailed power grid operation data can be obtained. By collecting real-time operation data of each module in the power grid, including key parameters such as the working status of the equipment (such as switch status, load condition), temperature, voltage, current, etc. During the collection process, the equipment status is analyzed in real time to determine whether there are any abnormalities (such as equipment overload, overheating, etc.), and the abnormal information is fed back to the monitoring system in real time. The collected raw data is cleaned (noise data is removed, missing data is processed, etc.) and converted into a standard format. According to the standard operation specifications of the power grid, a standard low-temperature power grid operation data set is generated, including real-time operation data, status information and any abnormal conditions of each module. The topological structure of the low-temperature power grid is combined with the geographic location data, and the power grid equipment is accurately located in three-dimensional space using the GIS system.The components and equipment data of the power grid (such as nodes, connections, loads, etc.) are converted into visual three-dimensional model data. Based on the components and geographic information data of the power grid, a three-dimensional spatial structure model of the power grid is constructed through modeling software (such as AutoCAD, Revit or other power engineering modeling tools). The model includes various types of equipment in the power grid (such as transformers, switches, transmission lines, etc.) and their accurate positions in three-dimensional space. The equipment status in the three-dimensional model is displayed in real time based on the collected data of the power grid operation (such as load, current, voltage, etc.), which helps the power grid operator to monitor the operating status of the equipment in real time and generate three-dimensional modeling data of the power grid operation, including the power grid structure, equipment parameters, operating status and environmental factors (such as temperature, humidity, etc.). These data can be used for further power grid analysis, fault diagnosis, performance optimization, etc.

[0075] Step S2: Based on the preset abnormal index threshold, the abnormal module of the low-temperature power grid operation three-dimensional modeling data is screened to obtain the abnormal module of the low-temperature power grid operation; the layered abnormal operation impact analysis is performed on the abnormal module of the low-temperature power grid operation to generate the abnormal impact factor of the low-temperature power grid operation; the cascade fault diffusion analysis is performed on the abnormal module of the low-temperature power grid operation through the abnormal impact factor of the low-temperature power grid operation to generate the cascade power fault diffusion data of the power grid;

[0076] In an embodiment of the present invention, abnormal indicators (such as temperature, load, voltage, current, equipment status, communication delay, etc.) are defined as monitoring indicators. The threshold of each indicator should be set based on the design standard and historical operation data of the power grid. For example, if the temperature of a transformer exceeds 70°C, a fault warning will be triggered, and voltage fluctuations exceeding ±10% will affect the stability of the power grid. A specific threshold is set for each indicator (for example, the temperature threshold is 70°C, and the current threshold is 120% of the rated current), and the device or module exceeding the threshold is 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 threshold. If an indicator of a module exceeds the preset threshold, it is marked as an abnormal module. All modules exceeding the threshold are screened out, including transformers, distribution equipment, transmission lines, switchgear, etc., to form a low-temperature power grid operation abnormal module set, and the generated abnormal module data includes the module identification, indicator value, threshold, abnormal time point and other information where the abnormality occurs. This data provides a basis for subsequent analysis. According to the structure and operation mode of the power grid, the abnormal modules are layered. Typical layering methods include equipment layer, subsystem layer, regional layer, etc. Abnormalities at different levels have different impacts on the power grid. Equipment level: failure of a single device, such as a transformer, switchgear, energy storage device, etc. Subsystem level: a subsystem composed of multiple devices (such as distribution network, transmission network, substation, etc.). Regional level: regional failure of the power grid, such as power supply interruption in a certain area. Define multiple impact factors to describe the severity of the abnormality. For example: the impact of load changes caused by abnormal modules on other modules. The impact of temperature increase caused by equipment abnormality on adjacent devices. The impact of abnormal voltage or current on other devices. Give each impact factor a different weight based on its contribution to the stability of the power grid. For example, the impact factor of current fluctuation has a higher weight, while the impact factor of temperature fluctuation has a lower weight. Analyze each abnormal device and calculate its impact on adjacent devices. For example, excessive transformer temperature causes nearby equipment to overload, thereby affecting the stability of the entire power grid. Analyze the impact of abnormal operation of the entire subsystem (such as a substation) on the surrounding area and evaluate the scope of the impact of power supply. When multiple subsystems or devices fail at the same time, evaluate the impact at the regional level of the power grid and generate abnormal impact factors for the power grid area. The analysis results of the equipment layer, subsystem layer and regional layer are integrated to generate the operation impact factor data of each abnormal module, including the degree of impact, scope of impact and severity rating at different levels. Cascading failure means that the failure of one module causes other modules connected to it to fail, and eventually spreads to the entire power grid. A cascading fault propagation model is established to simulate the diffusion process after the failure occurs. According to the topological structure of the power grid, the connection relationship between each module and other modules is defined to form a fault propagation network. Each module in the power grid is a node in the network, and the connection is the power flow path.According to the topological structure of the power grid and the influencing factors of the abnormal modules, simulate how the fault propagates from one module to other modules. The speed and path of fault propagation depend on the influencing factors of the abnormal modules and the network connection relationship. For example, when a substation has an abnormal current, its fault will be transmitted to the downstream area through the transmission line. Evaluate the scope and affected area of ​​the fault spread according to the structure and influencing factors of the power grid. If the voltage anomaly in a certain area spreads to the adjacent area, it will affect more equipment and systems. Record the occurrence time, propagation path, affected module, fault scale and other information of the cascading fault. This data can be used for further power grid restoration and optimization analysis. By calculating the total impact of the fault spread (such as the lost load, the affected area, the number of affected equipment, etc.), data support is provided for subsequent restoration and repair work.

[0077] Step S3: performing power failure risk prediction on the power grid cascade power failure diffusion data to generate power grid power failure risk prediction data; performing cascade operation optimization on the power grid cascade power failure diffusion data according to the power grid power failure risk prediction data to generate power grid cascade operation optimization data; constructing a power grid operation optimization plan based on the power grid cascade operation optimization data to generate a power grid cascade failure operation optimization plan;

[0078] In an embodiment of the present invention, by identifying the key factors affecting the risk of power failure in the power grid cascading fault diffusion data, such as load fluctuation, equipment health status, communication delay, environmental factors (such as temperature, humidity), etc. Collect and analyze the historical fault records of the power grid, establish a database containing different types of fault conditions, and provide reference data for fault risk prediction. Use Bayesian network, Markov chain, random forest or neural network and other methods to build a fault risk prediction model to predict the probability of fault occurrence. The model is trained and inferred based on information such as the topological structure of the power grid, historical fault data and current operating status. The power grid cascading fault diffusion data is preprocessed, including data cleaning, outlier removal, normalization, etc., to ensure the quality of the model input data. The power grid cascading power fault diffusion data is analyzed by the risk prediction model, and the fault risk level of each module or area is output. The output data includes: the probability of fault occurrence, the scope of influence of the potential fault module and the affected equipment, and the power grid fault risk prediction data is generated, including the probability of risk prediction, warning level, potential fault area and other information. This data can provide a basis for subsequent power grid optimization and fault prevention. The main goal of grid cascade operation optimization is to minimize the risk of fault propagation and ensure that the fault does not spread in the grid or limit the impact of the fault to the minimum range. Ensure that the grid can maintain load balance during operation and maintain system stability to avoid large-scale power supply interruptions. One of the optimization goals is to extend the service life of grid equipment, reduce the load peak of equipment, and avoid overload or overheating. Genetic algorithms can be used to optimize the topology of the grid so that when a fault occurs, the propagation of the fault can be reduced by reconfiguring the line or equipment. Particle swarm optimization algorithms can be used to dynamically adjust the load distribution of the grid and optimize the load flow to reduce the impact of the fault on the entire system. For the topology optimization of grid operation, the MILP model can be used to comprehensively optimize the various components of the grid (such as substations, transmission lines, load distribution, etc.) to ensure the optimal operation strategy. In the event of a fault, the load is transferred from the fault area to other healthy areas through the automatic reconfiguration system of the grid. The optimization process should be based on power load, system stability and risk prediction data, and give priority to paths that are not affected by the fault. Through the grid load flow optimization algorithm, the distribution of power flow is dynamically adjusted to avoid excessive load in local areas when faults occur, which may lead to chain reactions or system crashes. Through topology reconstruction and fault isolation, the structure of the grid is optimized to ensure that power flow can bypass the fault area and restore power supply through backup paths, generating optimized grid topology data, including grid component reconfiguration, load distribution, fault isolation and recovery paths. Output parameters in the optimization process, such as load adjustment values, equipment scheduling strategies, and the working status of each grid module.The goal of the power grid operation optimization scheme is to ensure that the fault area can be quickly isolated and the load distribution can be optimized through real-time monitoring and automatic control when a fault occurs, so as to maximize the stability of the power grid and minimize the fault loss. According to the power grid cascade operation optimization data, an automatic control response mechanism is designed to ensure that load adjustment and power grid reconfiguration can be quickly performed when a fault occurs. A fault detection system is designed to monitor the equipment status, load fluctuation, voltage change and other information in the power grid in real time to identify possible fault risks in a timely manner. After the fault occurs, the recovery path is automatically planned through the optimization algorithm to quickly switch from the fault area to the healthy area to ensure that the power supply is not interrupted. Through the distributed control system, each part of the power grid is controlled in real time to ensure that other parts of the power grid can continue to operate stably when a local fault occurs. Through simulation and historical data analysis, the effect of the power grid cascade fault operation optimization scheme is evaluated, including fault response time, recovery efficiency, system stability, etc. The optimization scheme is adjusted according to the evaluation results to further improve the disaster resistance, stability and operation efficiency of the power grid. Based on the above optimization process, a complete power grid cascade fault operation optimization scheme is generated, including fault detection, emergency response, automatic recovery path and load adjustment strategy.

[0079] Step S4: Perform an operation optimization performance evaluation based on the power grid cascading fault operation optimization plan to generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan to generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

[0080] In the embodiment of the present invention, the goal of evaluating the performance of power grid operation optimization is to evaluate various indicators such as the response speed, fault recovery capability, system stability, and load distribution efficiency of the power grid when a fault occurs after the optimization scheme is implemented. The main evaluation indicators include: whether the optimization scheme can respond to the fault in time and shorten the response time of fault handling. Whether the optimization scheme can effectively shorten the time for the power grid to return to normal operation. After the optimization scheme is implemented, whether the stability of the power grid is improved, whether it can maintain normal operation and avoid large-scale shutdown. Under the optimization scheme, whether the load distribution is reasonable to avoid overload or low-efficiency operation. Use simulation tools to perform virtual power grid operation tests, simulate different types of faults and external interference, and evaluate the actual effect of the optimization scheme. The simulation includes scenarios such as single-point faults, multiple-point faults, and sudden load fluctuations. Conduct small-scale field tests of the optimization scheme in some areas or modules, monitor the power grid response, fault recovery, and load distribution in real time, and collect field data for evaluation. Compare the evaluation data after the implementation of the optimization scheme with the data in the original unoptimized state to analyze the improvement of various indicators. Through the above evaluation methods, the power grid operation optimization performance evaluation data is generated, including data of various evaluation indicators such as response time, fault recovery time, power grid stability, load distribution efficiency, etc. These data can be used to judge the effectiveness and performance of the optimization plan. A detailed performance evaluation report is formed, which lists the changes before and after the implementation of the optimization plan to help decision makers understand the effect of the optimization plan. During the operation of the power grid, real-time feedback data after the implementation of the optimization plan is collected. These data include equipment status, load fluctuations, fault frequency, system response time, recovery time, etc. Through the installed monitoring equipment, real-time data of the power grid under different operating conditions, such as current, voltage, temperature, load distribution, etc., are collected to feedback the actual operation of the power grid. Feedback from power users, especially the response to power supply interruption and restoration, is collected to evaluate the impact of the optimization plan on users. Feedback data after the optimization implementation is analyzed to identify potential deficiencies in the optimization plan. For example, the fault recovery time in some areas is too long, or the load of some equipment is too high. Through a comprehensive analysis of the feedback data, problems existing in the implementation of the optimization plan are identified, such as slow response of some equipment, incomplete fault isolation, or uneven load distribution. According to the feedback data and evaluation results, it is confirmed which optimization measures have played a positive role and which need further improvement. According to the feedback results, adjust the optimization plan for existing problems. For example, optimize the load distribution strategy, adjust the grid topology, or strengthen fault detection and automatic response capabilities. According to the actual operation situation, improve the optimization algorithm used (such as genetic algorithm, particle swarm optimization, etc.) to better adapt to the actual operation needs of the power grid. In response to the response delay or overload of some equipment, adjust the equipment scheduling strategy to achieve a more balanced load distribution. In response to the problem of untimely response in some areas, optimize the emergency response mechanism to ensure rapid isolation and power restoration when a fault occurs.Based on the feedback data and analysis results, an updated grid cascading fault operation optimization plan is generated. The updated plan should include new optimization strategies, adjusted algorithms, improved equipment dispatch strategies, etc.

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

[0082] Step S11: obtaining low temperature power grid structure data;

[0083] Step S12: performing a grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; dividing 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 a power generation module, a power transmission module, a power distribution module, and a user power module;

[0084] Step S13: collecting grid operation data of the low-temperature grid based on the grid component module data to obtain low-temperature grid operation collection data; performing data preprocessing on the low-temperature grid operation collection data to generate standard low-temperature grid operation collection data, wherein the data preprocessing includes data denoising, data filtering, data normalization and data standardization;

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

[0086] In an embodiment of the present invention, structural data is obtained from sensors, data acquisition equipment and historical archives of the low-temperature power grid. Ensure that the data covers the main components of the power grid, including power generation equipment, transmission and distribution lines, switchgear and user terminal connections. The data format needs to support multi-dimensional descriptions, including geometric layout, physical parameters (such as resistance, capacitance, etc.) and environmental influencing factors (such as temperature and humidity). Apply graph theory methods to construct a topological graph of the low-temperature power grid based on nodes (grid components) and edges (electrical connections between components); determine topological characteristics such as network diameter, connectivity and redundancy to evaluate the robustness of the network. According to the function and topological structure of the power grid, it is divided into power generation module, transmission module, distribution module and user power module; use module partitioning algorithms (such as community detection algorithms) to ensure the logical consistency and physical rationality of the connection between modules; output module data, including module boundaries, equipment lists in the module and connection relationships between modules. Use a distributed sensor network to collect low-temperature power grid operation status data, including real-time voltage, current, power, frequency, etc.; ensure that the acquisition frequency is high enough to capture dynamic operation characteristics. Use wavelet transform or low-pass filter to remove noise; use Kalman filter to optimize signal quality; convert data to a unified scale for subsequent processing and analysis, and the generated standard low-temperature power grid operation acquisition data is consistent and highly reliable to support modeling needs. Combined with the standard low-temperature power grid operation acquisition data, a three-dimensional model based on physical laws and data-driven is constructed; three-dimensional modeling needs to consider the time dimension and generate a panoramic view of the dynamic operation scene; use simulation tools (such as MATLAB Simulink, ANSYS or self-developed simulation platform) to create the model. The three-dimensional modeling data of the low-temperature power grid operation includes the spatial position, operating status and dynamic change characteristics of the power grid components; the model should have high visualization and high interactivity to provide support for subsequent optimization and decision-making.

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

[0088] Step S141: extracting key operation data from the standard low-temperature power grid operation collection data to obtain key operation data of the low-temperature power grid, wherein the key operation data of the low-temperature power grid includes operation temperature data, voltage and current data, and power load data;

[0089] Step S142: spatially locate the power grid equipment on the low-temperature power grid structure data to generate power grid equipment coordinate data; and path-delineate the power grid equipment coordinate data to generate line direction data;

[0090] Step S143: spatially model the low-temperature power grid structure data through line direction data to generate low-temperature power grid spatial site layout data; import spatial site data into the low-temperature power grid spatial site layout data according to operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

[0091] In the embodiment of the present invention, the real-time record of the temperature sensor is obtained from the standard low-temperature power grid operation collection data; the temperature distribution characteristics are used to detect abnormal areas and mark hot spots. Real-time voltage and current data are extracted according to line and equipment classification; the extracted data is dynamically curve fitted to analyze the fluctuation characteristics. According to the user power module and the grid load balance, the total load and local load data are extracted; the load rate is calculated, the high-load area and potential bottlenecks are located, and the key operation data of the low-temperature power grid generated include key indicators of operating temperature, voltage, current and power load, which are convenient for reference in subsequent modeling links. Grid equipment, including transformers, switches, transmission lines, etc., are identified through grid structure data; a three-dimensional space coordinate system is generated based on the geographic coordinate data of the equipment, and the grid equipment coordinate data is output. According to the equipment coordinate data and the line topology, the connection path between the equipment is constructed; the optimal line direction is generated using a path optimization algorithm (such as the Dijkstra algorithm); the line direction data contains the equipment connection relationship and spatial path information. The spatial site layout modeling of the low-temperature power grid structure is performed based on the line direction data; the site location and functional classification (such as substation, user site, etc.) are determined, and the spatial site layout data of the low-temperature power grid is generated. Map key operating data (operating temperature, voltage and current, power load) to the corresponding spatial sites; use a multi-level modeling method to embed the operating data into the site model to reflect the actual operating status and generate three-dimensional modeling data for low-temperature power grid operation, including a complete spatial site layout and dynamic operating characteristics, to support subsequent analysis and visualization.

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

[0093] Step S21: performing grid anomaly monitoring on the low-temperature grid operation three-dimensional modeling data based on a preset abnormal index threshold to obtain low-temperature grid abnormal monitoring data;

[0094] Step S22: screening abnormal modules of the low-temperature power grid operation three-dimensional modeling data according to the low-temperature power grid abnormal monitoring data to obtain the low-temperature power grid operation abnormal module;

[0095] Step S23: performing hierarchical abnormal operation impact analysis on the low-temperature power grid operation abnormality module to generate a low-temperature power grid operation abnormality impact factor;

[0096] Step S24: performing cascading fault diffusion analysis on the low-temperature power grid operation abnormality module according to the low-temperature power grid operation abnormality influencing factors, and generating power grid cascading power fault diffusion data.

[0097] In an embodiment of the present invention, thresholds for various abnormal indicators are set based on historical data, expert experience, and grid characteristics. For example, the temperature exceeds a specific value, the voltage is too low, or the current fluctuates abnormally. The monitoring standard and alarm condition for each abnormal indicator are defined (such as a temperature threshold of 50°C and a voltage fluctuation amplitude of ±10%). Each monitoring data (such as voltage, current, temperature, etc.) 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; the real-time data stream and the historical data are compared to perform abnormal inspections on each site and module to monitor the operation status of the power grid. The abnormal monitoring data of the low-temperature power grid is automatically generated to mark the specific area or module where the abnormality occurs. According to the abnormal monitoring data of step S21, combined with the structural module division of the power grid, the modules with abnormalities are screened out; the degree of abnormality of each module is evaluated, such as calculating the frequency, duration, amplitude, and other indicators of the abnormality, and identifying the modules with greater impact. The screening criteria can be based on multiple factors, such as the degree of abnormality, the importance of the module (such as the power generation module or the substation module), and the risk of abnormal propagation. Abnormal modules are classified (such as power generation module, transmission module, and distribution module), and further classified according to their impact on the power grid (high, medium, and low impact), and data of abnormal modules of low-temperature power grid operation is generated, including the identification, classification, abnormal degree and related impact analysis of abnormal modules. The abnormal modules of low-temperature power grid operation are analyzed in layers according to the impact level. The stratification can be based on the criticality of the power grid module, the load characteristics, and the possibility of abnormal propagation. For example, the power generation module is specifically the most critical module in the power grid, and its abnormality will have a serious impact on the entire power grid, while the abnormality of the user terminal is limited to the local impact. At each level, the specific impact of the abnormal module on the overall operation of the power grid is analyzed, including power output, stability of transmission and distribution lines, load balance, etc. According to the properties of the abnormal module (such as current, voltage abnormality, high temperature, etc.), its direct impact factor on the power grid is calculated. The calculation of the impact factor can be completed through data regression analysis, fault simulation, or an impact propagation model based on the power grid topology structure, generating data on abnormal impact factors of low-temperature power grid operation, quantifying the impact of different abnormalities on the power grid, and helping to locate the fault area that needs to be handled first. Based on the impact factor of abnormal operation of low-temperature power grid, a power grid cascade fault propagation model is constructed. The model should consider factors such as the power transmission relationship between modules, equipment redundancy, and load transfer capacity. Use the fault propagation model to analyze the impact path of abnormal modules on other modules and simulate the fault diffusion process. Algorithms based on graph theory (such as fault propagation algorithms) can be used to derive fault chains. Based on model analysis, grid cascade power fault diffusion data is generated. This data shows how the fault spreads along the grid structure from the initial fault point and eventually affects the entire system. During the analysis, the speed of fault spread, the scale of impact, and the power equipment affected are calculated to assess the vulnerability of the grid.

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

[0099] Step S231: collecting basic power generation data of the power generation module in the low-temperature power grid operation abnormality module to obtain basic data of the power generation module; performing power generation cooling analysis on the basic data of the power generation module to generate cooling data of the power generation module; performing a first influencing factor conversion on the basic data of the power generation module based on the cooling data of the power generation module to generate an influencing factor of the power generation module;

[0100] Step S232: collecting basic transmission data of the transmission module in the low-temperature power grid operation abnormality module to obtain basic data of the transmission module; evaluating the line icing load state of the basic data of the transmission module to generate line evaluation data of the transmission module; performing insulation performance analysis on the basic data of the transmission module using the line evaluation data of the transmission module to generate insulation performance data of the transmission module; performing a second influencing factor conversion on the basic data of the power generation module based on the insulation performance data of the transmission module to generate an influencing factor of the transmission module;

[0101] Step S233: collecting basic data of power transmission from the power distribution module in the low-temperature power grid operation abnormality module to obtain basic data of the power distribution module; performing power grid cooling efficiency analysis on the basic data of the power distribution module to generate power distribution cooling efficiency data; performing a third influencing factor conversion on the basic data of the power distribution module based on the power distribution cooling efficiency data to generate an influencing factor of the power distribution module;

[0102] Step S234: collecting basic power consumption data of the user power consumption module in the low-temperature power grid operation abnormality module to obtain basic power consumption module data; performing power grid load characteristic analysis on the basic power consumption module data to generate power consumption load characteristic data; performing a fourth influencing factor conversion on the basic power consumption module data based on the power consumption load characteristic data to generate a power consumption module influencing factor;

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

[0104] In an embodiment of the present invention, basic data including real-time monitoring data such as power generation, temperature data, and flow rate are extracted from the power generation module in the low-temperature power grid operation abnormality module, and these 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. The cooling efficiency is calculated, with special attention paid to the situation where the temperature is too high or the flow rate is insufficient, and the abnormal area is marked. The cooling data of the power generation module is generated according to the cooling effect to further analyze the influencing factors. The influencing factors are calculated based on the cooling data of the power generation module. The temperature sensitivity and cooling capacity of the power generation system are mainly focused on. The specific formula for calculating the influencing factors may include cooling rate, temperature deviation, etc. as input conditions to generate the power generation module influencing factors so as to comprehensively analyze the influencing factors in subsequent steps. Basic data including real-time monitoring data such as line load, voltage, and temperature are extracted from the transmission module in the low-temperature power grid operation abnormality module, which includes real-time status monitoring and load data of the transmission line. The icing condition and load state of the transmission line are evaluated, taking into account meteorological conditions, load capacity, and mechanical strength of the line. Line evaluation data is generated according to the icing condition, and abnormal icing or overload conditions are marked. Use line assessment data to analyze the insulation performance of the transmission module. Pay attention to the temperature and voltage data that affect line safety, ensure that the line is within the normal or safe operating range, and generate insulation performance data for further calculation of impact factors. Calculate the impact factors based on the insulation performance data of the transmission module. Focus on the electrical stability and load conditions of the line. Use specific formulas (such as temperature and voltage deviation) to calculate the impact factors and generate the transmission module impact factors for subsequent comprehensive analysis. Extract basic data from the distribution module in the low-temperature power grid operation abnormality module, including real-time monitoring data such as current, voltage distribution, and temperature, which can help evaluate the operating status of the distribution system. Analyze the cooling efficiency of the distribution module, focusing on temperature and load balance. Cooling efficiency will affect the life and safety of the distribution equipment, generate distribution cooling efficiency data, and mark insufficient cooling or excessive temperature. Calculate the impact factors based on the cooling efficiency data of the distribution module. Focus on equipment temperature and load capacity. Use specific formulas (such as temperature difference and voltage adjustment range) to calculate the impact factors and generate the distribution module impact factors for subsequent comprehensive impact analysis. Extract basic data from the user power consumption module in the low-temperature power grid operation abnormality module, including real-time data such as load level, voltage stability, and power consumption. Analyze the load characteristics of the user power consumption module, focus on peak load, balance, and usage characteristics, generate power load characteristic data, and mark abnormal power consumption or excessive load fluctuations. Calculate the impact factor based on the power load characteristic data. Focus on the stability of power consumption and load changes. Use specific formulas (such as the load stability index) to calculate the impact factor and generate the user power consumption module impact factor for subsequent overall power grid impact analysis.The generated power generation module impact factors, transmission module impact factors, distribution module impact factors and user power module impact factors are integrated. Use weighted average, statistical methods or comprehensive evaluation models to comprehensively calculate the impact factors of abnormal operation of low-temperature power grid. Considering the weight and importance of each impact factor, the final impact factors of abnormal operation of low-temperature power grid are generated. These impact factors can 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: performing threshold detection on the factors affecting the abnormal operation of the low-temperature power grid to generate fault source location data; classifying the fault type of the fault source location data to generate fault feature data; evaluating the severity of the fault feature data to generate fault level data;

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

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

[0109] In the embodiment of the present invention, the threshold detection is performed on the abnormal influencing factors of the low-temperature power grid operation. According to the preset threshold, which modules or components have an operating state exceeding the normal threshold and are determined to be potential fault sources. A data-driven method (such as anomaly detection algorithm, machine learning model, etc.) is used to identify abnormal areas, and fault source location data is generated to indicate the area or equipment where the fault occurs. Based on the fault source location data, the fault source is classified by type. The classification criteria may include equipment failure, line failure, load imbalance, environmental impact, etc. The fault type is calibrated using a classification algorithm (such as a decision tree, support vector machine, etc.) to generate fault feature data. According to the fault feature data, the severity of the fault is evaluated. The evaluation criteria include the impact range of the fault on the power grid, voltage deviation, power loss, etc. The weighted scoring model or multi-level analysis method is used to grade the fault, generate fault level data, indicate the severity of the fault, generate fault source location data, fault type classification data and fault level data, which are used for subsequent propagation path prediction and fault diffusion analysis. Connectivity analysis is performed on the structural topology data of the low-temperature power grid to evaluate the connection relationship between the modules, especially the network connectivity of the area around the fault source. Use graph theory analysis methods (such as node degree, connectivity analysis, shortest path algorithm, etc.) to generate network connection data to indicate the connection strength and stability between different nodes in the power grid. Perform propagation path prediction based on fault level data and network connection data. Combine power grid topology, fault level and impact factor to predict the path of fault propagation from the source. Use propagation models (such as information diffusion model, fault propagation simulation, etc.) to predict the path of fault propagation and generate path prediction data. Perform propagation timing analysis on path prediction data to evaluate the impact of faults on the power grid at different time points. Focus on the expansion speed, impact time and step-by-step transmission delay of the fault. Use timing analysis methods (such as time series analysis, dynamic models, etc.) to generate timing feature data to indicate the time characteristics of the fault propagation process, generate path prediction data and timing feature data, and provide input for subsequent fault propagation simulation and spatiotemporal evolution analysis. Based on the timing feature data, perform fault propagation simulation on the propagation path prediction data to simulate the process of faults extending from the source to other parts of the power grid. Use simulation models (such as dynamic system models, fluid propagation models, etc.) to simulate the diffusion process of faults and generate diffusion process data to indicate the speed, scope and impact of fault propagation. Perform spatiotemporal evolution analysis on the diffusion process data to observe the evolution pattern of faults in spatial and temporal dimensions. Analyze the impact of fault propagation on the spatial distribution and temporal changes of the power grid. Use spatiotemporal data analysis methods (such as spatial statistical models, spatiotemporal matrices, etc.) to study the evolution law of fault diffusion and generate evolution pattern data. Using evolution pattern data, calculate the influence domain of the abnormal operation module of the low-temperature power grid and analyze the impact of the fault propagation process on each module and region of the power grid.Calculate the number of affected areas, devices and nodes in the power grid, as well as the severity of their faults, to generate power grid cascading power fault diffusion data, generate diffusion process data, spatiotemporal evolution analysis data and power grid cascading power fault diffusion data to evaluate the overall impact of fault diffusion and guide the power grid restoration strategy.

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

[0111] Step S31: dividing the data set of the power grid cascade power fault diffusion data to generate a model training set and a model test set; using a random forest algorithm to perform model training on the model training set to generate a power grid cascade fault risk assessment pre-model;

[0112] Step S32: optimizing and iterating the pre-model of the power grid cascading failure risk assessment through the model test set, thereby generating a power grid cascading failure risk assessment model; importing the power grid cascading power failure diffusion data into the power grid cascading failure risk assessment model to perform power failure risk prediction, thereby generating power grid power failure risk prediction data;

[0113] Step S33: marking the grid cascade power fault diffusion data with fault risk levels according to the grid power fault risk prediction data to generate the grid cascade power fault risk level; performing cascade operation optimization on the grid cascade power fault risk level using the grid cascade control optimization formula to generate grid cascade operation optimization data;

[0114] Step S34: constructing a power grid operation optimization plan for the cascade power failure risk level based on the power grid cascade operation optimization data, thereby generating a power grid cascade failure operation optimization plan.

[0115] In an embodiment of the present invention, the data set is divided into a training set and a test set by dividing the data of the power grid cascade power fault diffusion data. Usually 70%-80% of the data is used for the training set, and the rest is used for the test set. When dividing, the diversity and representativeness of the data should be ensured so that the model can effectively learn the characteristics of the power grid fault risk assessment. The training set is trained using the random forest algorithm. The random forest algorithm generates an efficient prediction model by constructing multiple decision trees and combining their results. During the training process, the model will learn the relationship between different fault diffusion characteristics and power grid risks, and use this information to generate a pre-model for the assessment of the risk of cascading faults in the power grid. The pre-model for the assessment of the risk of cascading faults in the power grid is verified and optimized by the model test set. In this process, the performance of the model will be tested by evaluation indicators (such as accuracy, recall rate, F1 value, etc.). According to the evaluation results of the model, parameter adjustment (for example, the number of trees, depth, minimum sample split number, etc.) is performed to achieve the optimization iteration of the model. After multiple rounds of iterations, the prediction performance of the model will be significantly improved, and a power grid cascade fault risk assessment model will be generated. The grid cascade power fault diffusion data is input into the optimized grid cascade fault risk assessment model to predict the power fault risk. Based on the input data, the model will output the fault risk assessment results of each module of the grid, and generate grid power fault risk prediction data, generate grid power fault risk prediction data, provide risk prediction of each module of the grid, and provide a basis for subsequent risk management and optimization. According to the grid power fault risk prediction data, the grid cascade power fault diffusion data is labeled with fault risk levels. The risk level labeling divides the fault risk into different levels (for example, low risk, medium risk, and high risk) according to the preset standards. The labeling process is usually based on the output of the model and combined with the actual grid operation standards. The grid cascade power fault risk level is optimized by using the grid cascade control optimization formula. The optimization formula comprehensively considers grid dispatching, load distribution, backup power resources, etc. under different risk levels, aiming to improve the grid operation efficiency and reduce the probability of failure. The goal of this step is to reduce the risk impact in the system and enhance the robustness and fault tolerance of the grid by optimizing the dispatching strategy of the grid. Based on the grid cascade operation optimization data, a grid fault operation optimization scheme is constructed. The solution takes into account the optimized dispatch data, grid load, backup system configuration and other dispatch strategies. Through simulation and optimization algorithms, the emergency response strategy of each module in the event of a failure is determined to ensure that the grid system can quickly recover and maintain power supply stability in the event of a cascading failure. The optimization solution is verified and adjusted to evaluate its applicability and effectiveness in the actual environment. During the verification process, testing can be performed using historical fault data or simulation data. If necessary, the optimization solution is adjusted and improved through a feedback mechanism to ensure that the grid has a better response strategy when facing potential future failures.

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

[0117]

[0118] In the formula, is the optimization target value of the power grid cascade operation, N is the total number of power grid nodes, and w i Expressed as the importance weight coefficient of the i-th node, P i,actual Expressed as the actual power of the i-th node, P i,max Denotes the maximum allowable power of the ith node, ΔP i Expressed as the power fluctuation of the i-th node, It is represented as the time derivative of the power change of the ith node, t is represented as the power change time, α is represented as the weight coefficient of the power fluctuation amount, and β is represented as the weight coefficient of the power change rate.

[0119] The present invention analyzes and integrates a grid cascade control optimization formula, which integrates multiple key factors, including: node importance weight w i By assigning weights, we focus on nodes that are critical to the operation of the power grid and ensure that important nodes are optimized first. Reflects the ratio of the actual power of the node to its capacity, avoiding node overload or resource waste. Power fluctuation ΔP i Capture short-term power fluctuations and reduce the risk of failure caused by fluctuations. By focusing on the rate of power change, the sudden fluctuation problem in the power grid can be controlled. The formula has dynamic optimization capabilities, can capture rapid changes in grid status in real time, adapt to complex operating environments, and improve the timeliness and accuracy of regulation. By comprehensively considering the power fluctuation amount and change rate, the formula can provide early warning of cascading failures, and prioritize high-risk nodes during optimization, significantly reducing the risk level of grid failures. Optimization target value The calculation of takes into account the power allocation and node importance weights, thereby achieving the optimal allocation of resources and improving the overall operation efficiency of the power grid. The parameters in the formula (such as ɑ, β and weight w i) has adjustment space and can be flexibly adjusted according to different grid operation requirements, so it is suitable for grid systems of various sizes and complexities. When using the conventional grid cascade control optimization formula in this field, the grid cascade operation optimization target value can be obtained. By applying the grid cascade control optimization formula provided by the present invention, the grid cascade operation optimization target value can be calculated more accurately. This formula can improve the operation efficiency and control flexibility of the grid while ensuring safety and reliability by quantifying and optimizing multiple key indicators of grid operation, and is particularly suitable for operation optimization tasks of complex cascade grids.

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

[0121] Step S41: collecting operation feedback data based on the power grid cascading fault operation optimization scheme to obtain power grid cascading fault operation optimization feedback data; performing operation optimization performance evaluation on the power grid cascading fault operation optimization feedback data to generate power grid operation optimization performance evaluation data;

[0122] Step S42: using the grid cascading fault operation optimization feedback data to update the grid cascading fault operation optimization scheme, generating a grid cascading fault operation optimization update scheme to perform low-temperature grid operation optimization operations.

[0123] In an embodiment of the present invention, after executing the grid cascade fault operation optimization scheme, the operation of the grid is monitored in real time, and relevant feedback data are collected, including grid load changes, fault frequency, voltage stability, equipment status, and power transmission efficiency. Feedback data collection can be performed through sensors installed at key nodes of the grid, monitoring systems, and real-time data streams. The data should cover all links, including the actual operation of power generation, transmission, distribution, and user terminals. The collected operation feedback data is analyzed in detail to evaluate the effect of the grid operation optimization scheme. The key indicators of the evaluation include the fault recovery time of the grid, system reliability, resource utilization, power loss, operating cost, etc. The performance evaluation model is used to compare the grid operation performance before and after optimization, and the grid operation optimization performance evaluation data is generated. 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.), generate grid operation optimization performance evaluation data, evaluate the effect of the optimization scheme in actual operation, and provide a basis for improving the optimization scheme. According to the operation optimization performance evaluation data, analyze the shortcomings of the existing optimization scheme, and make necessary adjustments and optimizations, including changing the grid dispatching strategy, optimizing the load distribution scheme, improving the redundancy of key equipment, and adding fault recovery strategies. In the process of updating the scheme, the special needs of the low-temperature power grid should be considered, especially in the extremely low temperature environment, the equipment of the power grid faces additional load pressure and failure risks. Therefore, the scheme update needs to focus on the robustness, resilience and adaptability of the system. Apply the updated grid cascading fault operation optimization scheme to the actual operation of the low-temperature power grid, which includes implementing new dispatching schemes, adjusting load distribution, and executing new fault emergency plans to improve the stability and reliability of the power grid in low temperature environments. During the implementation process, continue to monitor the operation status of the power grid to ensure the effectiveness of the scheme, and make necessary fine-tuning and real-time optimization according to the actual operation situation, generate a grid cascading fault operation optimization update scheme, implement low-temperature power grid operation optimization operations, and provide a continuous optimization scheme for the long-term stable operation of the power grid.

[0124] In this specification, a low-temperature power grid operation safety monitoring system based on an intelligent algorithm is provided, which is used to execute the low-temperature power grid operation optimization method of the above-mentioned intelligent algorithm. The low-temperature power grid operation safety monitoring system based on the intelligent algorithm includes:

[0125] The power grid modeling module is used to obtain the 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data;

[0126] The cascading fault analysis module is used to screen abnormal modules of the three-dimensional modeling data of low-temperature power grid operation based on the preset abnormal index threshold to obtain abnormal modules of low-temperature power grid operation; perform layered abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal impact factors of low-temperature power grid operation; perform cascading fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal impact factors of low-temperature power grid operation to generate grid cascading power fault diffusion data;

[0127] The power grid operation optimization module is used to predict the power grid cascade power fault diffusion data for power grid and generate power grid power fault risk prediction data; perform cascade operation optimization on the power grid cascade power fault diffusion data according to the power grid power fault risk prediction data and generate power grid cascade operation optimization data; construct a power grid operation optimization plan based on the power grid cascade operation optimization data, thereby generating a power grid cascade fault operation optimization plan;

[0128] The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascading fault operation optimization plan and generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan and generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

[0129] The beneficial effect of the present invention is that by acquiring the low-temperature power grid structure data and dividing the power grid component modules, the systematicness and hierarchy of the power grid are ensured. By collecting the power grid operation data and performing three-dimensional modeling, the operation data of the low-temperature power grid is generated, the visualization and accuracy of the power grid operation are improved, which is helpful to fully understand the operation status and potential problems of the power grid, thereby laying the foundation for subsequent optimization and fault analysis. By screening the abnormal module based on the preset abnormal index threshold, the potential fault area in the power grid can be identified in time, thereby avoiding the risk of outage across the entire network. Through hierarchical abnormal impact analysis and cascade fault diffusion analysis, the module effectively predicts and tracks the path of fault propagation, can accurately assess the scope and degree of fault impact, and improves the early warning of fault detection and the accuracy of the response strategy. By predicting the risk of power failure and optimizing the cascade operation, the risk of large-scale failures in the power grid is effectively reduced. By constructing a power grid operation optimization scheme, the operation of the power grid can be dynamically adjusted, the power grid resource configuration can be optimized, the operation efficiency and stability of the power grid in a low-temperature environment can be improved, and the sustainability of the power grid operation can be guaranteed. By evaluating the performance of the power grid operation optimization scheme, the effectiveness of the optimization scheme can be measured, providing a basis for subsequent scheme improvements. The optimization scheme is updated using feedback data to ensure the efficient response capability of the power grid in different operating environments and fault conditions. Through continuous optimization, the overall operating efficiency, fault response capability and energy utilization of the power grid are improved. Therefore, the present invention improves the safety and intelligence of low-temperature power grid operation through intelligent modular analysis, fault diffusion prediction and optimization, and real-time feedback mechanism.

[0130] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0131] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be 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 present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A low temperature power grid operation optimization method based on intelligent algorithm, characterized in that: The following steps are involved: Step S1: 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; Based on the data of the power grid component modules, the power grid operation data of the low-temperature power grid is collected to obtain the standard low-temperature power grid operation collection data; Conduct three-dimensional modeling of power grid operation on the standard low-temperature power grid operation collection data to generate three-dimensional modeling data of low-temperature power grid operation; Step S2: screening abnormal modules of the low-temperature power grid operation three-dimensional modeling data based on a preset abnormal index threshold to obtain a low-temperature power grid operation abnormal module; Conduct hierarchical abnormal operation impact analysis on the low-temperature power grid operation abnormality module and generate the low-temperature power grid operation abnormality impact factor; The cascading fault diffusion analysis of the low-temperature power grid operation abnormality module is carried out through the low-temperature power grid operation abnormality influencing factors to generate the power grid cascading power fault diffusion data; Step S3: Perform power failure risk prediction on the power grid cascade power failure diffusion data to generate power grid power failure risk prediction data; Optimize the cascade operation of the power grid cascade power fault diffusion data according to the power grid power fault risk prediction data to generate power grid cascade operation optimization data; Construct a power grid operation optimization plan based on the power grid cascade operation optimization data, thereby generating a power grid cascade fault operation optimization plan; Step S4: Perform an operation optimization performance evaluation based on the power grid cascading fault operation optimization plan to generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan to generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

2. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: obtaining low temperature power grid structure data; Step S12: performing a grid structure topology analysis on the low-temperature grid structure data to generate low-temperature grid structure topology data; dividing 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 a power generation module, a power transmission module, a power distribution module, and a user power module; Step S13: collecting grid operation data of the low-temperature grid based on the grid component module data to obtain low-temperature grid operation collection data; performing data preprocessing on the low-temperature grid operation collection data to generate standard low-temperature grid operation collection data, wherein the data preprocessing includes data denoising, data filtering, data normalization and data standardization; Step S14: Perform three-dimensional modeling of the operation of the power grid on the standard low-temperature power grid operation collected data to generate three-dimensional modeling data of the operation of the low-temperature power grid.

3. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: extracting key operation data from the standard low-temperature power grid operation collection data to obtain key operation data of the low-temperature power grid, wherein the key operation data of the low-temperature power grid includes operation temperature data, voltage and current data, and power load data; Step S142: spatially locate the power grid equipment on the low-temperature power grid structure data to generate power grid equipment coordinate data; and path-delineate the power grid equipment coordinate data to generate line direction data; Step S143: spatially model the low-temperature power grid structure data through line direction data to generate low-temperature power grid spatial site layout data; import spatial site data into the low-temperature power grid spatial site layout data according to operating temperature data, voltage and current data, and power load data to generate low-temperature power grid operation three-dimensional modeling data.

4. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: performing grid anomaly monitoring on the low-temperature grid operation three-dimensional modeling data based on a preset abnormal index threshold to obtain low-temperature grid abnormal monitoring data; Step S22: screening abnormal modules of the low-temperature power grid operation three-dimensional modeling data according to the low-temperature power grid abnormal monitoring data to obtain the low-temperature power grid operation abnormal module; Step S23: performing hierarchical abnormal operation impact analysis on the low-temperature power grid operation abnormality module to generate a low-temperature power grid operation abnormality impact factor; Step S24: performing cascading fault diffusion analysis on the low-temperature power grid operation abnormality module according to the low-temperature power grid operation abnormality influencing factors, and generating power grid cascading power fault diffusion data.

5. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 4 is characterized in that: Step S23 includes the following steps: Step S231: collecting basic power generation data of the power generation module in the low-temperature power grid operation abnormality module to obtain basic data of the power generation module; performing power generation cooling analysis on the basic data of the power generation module to generate cooling data of the power generation module; performing a first influencing factor conversion on the basic data of the power generation module based on the cooling data of the power generation module to generate an influencing factor of the power generation module; Step S232: collecting basic transmission data of the transmission module in the low-temperature power grid operation abnormality module to obtain basic data of the transmission module; evaluating the line icing load state of the basic data of the transmission module to generate line evaluation data of the transmission module; performing insulation performance analysis on the basic data of the transmission module using the line evaluation data of the transmission module to generate insulation performance data of the transmission module; performing a second influencing factor conversion on the basic data of the power generation module based on the insulation performance data of the transmission module to generate an influencing factor of the transmission module; Step S233: collecting basic data of power transmission from the power distribution module in the low-temperature power grid operation abnormality module to obtain basic data of the power distribution module; performing power grid cooling efficiency analysis on the basic data of the power distribution module to generate power distribution cooling efficiency data; performing a third influencing factor conversion on the basic data of the power distribution module based on the power distribution cooling efficiency data to generate an influencing factor of the power distribution module; Step S234: collecting basic power consumption data of the user power consumption module in the low-temperature power grid operation abnormality module to obtain basic power consumption module data; performing power grid load characteristic analysis on the basic power consumption module data to generate power consumption load characteristic data; performing a fourth influencing factor conversion on the basic power consumption module data based on the power consumption load characteristic data to generate a power consumption module influencing factor; Step S235: integrating the power generation module influence factor, the power transmission module influence factor, the power distribution module influence factor and the power consumption module influence factor to generate the low-temperature power grid operation abnormality influence factor.

6. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 4 is characterized in that: Step S24 includes the following steps: Step S241: performing threshold detection on the factors affecting the abnormal operation of the low-temperature power grid to generate fault source location data; classifying the fault type of the fault source location data to generate fault feature data; evaluating the severity of the fault feature data to generate fault level data; Step S242: performing connectivity analysis on the low-temperature power grid structure topology data to generate network connection data; performing propagation path prediction on the fault level data and the network connection data to generate path prediction data; performing propagation timing analysis on the path prediction data to generate timing feature data; Step S243: Perform fault diffusion simulation on the path prediction data according to the time series feature data to generate diffusion process data; perform spatiotemporal evolution analysis on the diffusion process data to generate evolution pattern data; use the evolution pattern data to calculate the influence domain of the low-temperature power grid operation abnormality module to generate power grid cascade power fault diffusion data.

7. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: dividing the data set of the power grid cascade power fault diffusion data to generate a model training set and a model test set; using a random forest algorithm to perform model training on the model training set to generate a power grid cascade fault risk assessment pre-model; Step S32: optimizing and iterating the pre-model of the power grid cascading failure risk assessment through the model test set, thereby generating a power grid cascading failure risk assessment model; importing the power grid cascading power failure diffusion data into the power grid cascading failure risk assessment model to perform power failure risk prediction, thereby generating power grid power failure risk prediction data; Step S33: marking the grid cascade power fault diffusion data with fault risk levels according to the grid power fault risk prediction data to generate the grid cascade power fault risk level; performing cascade operation optimization on the grid cascade power fault risk level using the grid cascade control optimization formula to generate grid cascade operation optimization data; Step S34: constructing a power grid operation optimization plan for the cascade power failure risk level based on the power grid cascade operation optimization data, thereby generating a power grid cascade failure operation optimization plan.

8. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 7 is characterized in that: The grid cascade control optimization formula in step S33 is as follows: In the formula, is the optimization target value of the power grid cascade operation, N is the total number of power grid nodes, and w i Expressed as the importance weight coefficient of the i-th node, P i,actual Expressed as the actual power of the i-th node, P i,max Denotes the maximum allowable power of the ith node, ΔP i Expressed as the power fluctuation of the i-th node, It is represented as the time derivative of the power change of the ith node, t is represented as the power change time, α is represented as the weight coefficient of the power fluctuation amount, and β is represented as the weight coefficient of the power change rate.

9. The low-temperature power grid operation optimization method based on intelligent algorithm according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: collecting operation feedback data based on the power grid cascading fault operation optimization scheme to obtain power grid cascading fault operation optimization feedback data; performing operation optimization performance evaluation on the power grid cascading fault operation optimization feedback data to generate power grid operation optimization performance evaluation data; Step S42: using the grid cascading fault operation optimization feedback data to update the grid cascading fault operation optimization scheme, generating a grid cascading fault operation optimization update scheme to perform low-temperature grid operation optimization operations.

10. A low-temperature power grid operation safety monitoring system based on intelligent algorithm, characterized in that: Used to execute the low-temperature power grid operation optimization method based on intelligent algorithm as claimed in claim 1, the low-temperature power grid operation safety monitoring system based on intelligent algorithm includes: The power grid modeling module is used to obtain the 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 of the low-temperature power grid based on the power grid component module data to obtain standard low-temperature power grid operation collection data; perform power grid operation three-dimensional modeling on the standard low-temperature power grid operation collection data to generate low-temperature power grid operation three-dimensional modeling data; The cascading fault analysis module is used to screen abnormal modules of the three-dimensional modeling data of low-temperature power grid operation based on the preset abnormal index threshold to obtain abnormal modules of low-temperature power grid operation; perform layered abnormal operation impact analysis on the abnormal modules of low-temperature power grid operation to generate abnormal impact factors of low-temperature power grid operation; perform cascading fault diffusion analysis on the abnormal modules of low-temperature power grid operation through the abnormal impact factors of low-temperature power grid operation to generate grid cascading power fault diffusion data; The power grid operation optimization module is used to predict the power grid cascade power fault diffusion data for power grid and generate power grid power fault risk prediction data; perform cascade operation optimization on the power grid cascade power fault diffusion data according to the power grid power fault risk prediction data and generate power grid cascade operation optimization data; construct a power grid operation optimization plan based on the power grid cascade operation optimization data, thereby generating a power grid cascade fault operation optimization plan; The performance evaluation module is used to evaluate the operation optimization performance based on the power grid cascading fault operation optimization plan and generate power grid operation optimization performance evaluation data; use the power grid cascading fault operation optimization feedback data to update the power grid cascading fault operation optimization plan and generate a power grid cascading fault operation optimization update plan to perform low-temperature power grid operation optimization operations.

Images