Power grid emergency dispatching method, device and equipment and storage medium

Abstract

The application provides a power grid emergency scheduling method and device, equipment and storage medium, relates to the power system repair scheduling technical field. The method comprises the following steps: in response to an emergency scheduling trigger event for a target substation, obtaining a device requirement list; based on the device requirement list, determining a candidate backup site, and obtaining the resource matching degree, importance index and correlation influence coefficient reflecting the cascading risk of the power grid of each candidate backup site; for each candidate backup site, determining the scheduling path distance from the site to the target substation according to the dynamic road network data fused with real-time meteorological data and real-time traffic control information; based on the scheduling path distance, the resource matching degree, the importance index and the correlation influence coefficient, evaluating each candidate backup site; according to the evaluation result, determining the target scheduling site and generating a scheduling scheme. The application significantly improves the efficiency, reliability and safety of power emergency scheduling in disaster scenarios through a multi-dimensional evaluation system.

Description

Technical Field

[0001] This application relates to the field of power system emergency repair and dispatching technology, and in particular to a power grid emergency dispatching method, device, equipment and storage medium. Background Technology

[0002] In power systems, substations are core nodes in grid operation, and equipment failures in these substations can trigger large-scale power outages or even grid collapse. Especially in scenarios with frequent natural disasters such as typhoons, torrential rains, and earthquakes, the risk of substation equipment losing power due to environmental degradation or physical damage increases significantly. For example, torrential rains can cause road flooding and traffic control, hindering the transport of emergency supplies; strong winds can cause physical damage to equipment, leading to cascading grid failures. In such disaster scenarios, power dispatching departments need to quickly locate the faulty equipment and allocate replacement materials from backup sites to the fault location to restore power and prevent the fault from spreading.

[0003] In related technologies, a static dispatching scheme based on Geographic Information System (GIS) is commonly used. Its typical execution process is as follows: when a substation fails, dispatchers first locate the faulty site in the GIS system; then, based on the equipment ledger database, they manually retrieve matching backup equipment information; next, using the fault point as the center, they sort surrounding spare parts depots on an electronic map according to straight-line distance or preset road distance; finally, they select the nearest spare parts depot as the dispatch source, plan transportation routes based on historical road network data, and issue dispatch instructions for execution. However, this still falls short of meeting the needs for efficient and safe emergency dispatching in disaster scenarios. Summary of the Invention

[0004] This application provides a power grid emergency dispatch method, apparatus, equipment, and storage medium to improve the problem that related technologies are unable to meet the needs of efficient and safe emergency dispatch in disaster scenarios.

[0005] Firstly, this application provides a power grid emergency dispatch method, including:

[0006] In response to emergency dispatch events triggered for the target substation, obtain a list of equipment requirements;

[0007] Based on the equipment requirement list, at least one candidate backup site is identified, and the resource matching degree, importance index, and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site are obtained.

[0008] For each candidate backup site, the dispatch path distance from the candidate backup site to the target substation is determined based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information.

[0009] Each candidate backup site is evaluated based on scheduling path distance, resource matching degree, importance index, and correlation impact coefficient;

[0010] Based on the evaluation results, the target scheduling site is determined from each candidate backup site, and the corresponding scheduling scheme is generated.

[0011] In one possible implementation, the scheduling path distance from the candidate backup site to the target substation is determined based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information. This includes: acquiring real-time meteorological data and real-time traffic control information; determining the real-time meteorological impact factors of each road segment in the road network between the candidate backup site and the target substation based on the real-time meteorological data; determining the traffic control status of each road segment based on the real-time traffic control information; dynamically determining the traffic weight of each road segment in the dynamic road network data based on the basic length of each road segment, the corresponding real-time meteorological impact factors, and the traffic control status; and using a path planning algorithm to determine the shortest feasible path from the candidate backup site to the target substation based on the traffic weight of each road segment in the dynamic road network data, and determining the path length of the shortest feasible path as the scheduling path distance.

[0012] In one possible implementation, the real-time meteorological impact factor includes a precipitation coefficient and a wind force coefficient. Based on the basic length of each road segment, the corresponding real-time meteorological impact factor, and the traffic control status, the traffic weight of each road segment in the dynamic road network data is dynamically determined. This includes: for the first road segment marked as prohibited by traffic control, the traffic weight of the first road segment is set to infinity or a preset maximum value; for the second road segment marked as permitted by traffic control, a meteorological impact adjustment coefficient is determined based on the precipitation coefficient and wind force coefficient of the second road segment, and the product of the basic length of the second road segment and the meteorological impact adjustment coefficient is used as the traffic weight of the second road segment in the dynamic road network data.

[0013] In one possible implementation, each candidate backup site is evaluated based on scheduling path distance, resource matching degree, importance index, and correlation impact coefficient. This includes: determining an accessibility score based on scheduling path distance (the shorter the scheduling path distance, the higher the accessibility score); determining a resource score based on resource matching degree (the higher the resource matching degree, the higher the resource score); determining an importance score based on importance index (the higher the importance index, the higher the importance score); determining a security score based on correlation impact coefficient (the lower the grid cascading risk represented by the correlation impact coefficient, the higher the security score); and then weighted summing the accessibility score, resource score, importance score, and security score to obtain the evaluation result of the candidate backup site.

[0014] In one possible implementation, the emergency dispatch trigger event is triggered by continuously monitoring the geological risk value of the target substation; when the geological risk value is greater than or equal to a preset risk trigger threshold, an emergency dispatch trigger event is determined to have occurred; wherein, the geological risk value is determined based on real-time precipitation data, real-time wind data, and geological topography data of the area where the target substation is located.

[0015] In one possible implementation, determining at least one candidate backup site based on the equipment demand list includes: defining a search range centered on the target substation according to a preset geographical search radius; and retrieving sites located within the search range and whose equipment inventory meets the equipment demand list from a preset backup site database as candidate backup sites.

[0016] In one possible implementation, the power grid emergency dispatch method further includes a dynamic correction step for the dispatch plan: after generating the dispatch plan, continuously monitor real-time meteorological data, real-time traffic control information, and the equipment inventory status of each candidate backup site; when any of the following dynamic change events are detected, trigger a re-evaluation and generation of the dispatch plan: a new traffic control section is added to the transportation route corresponding to the dispatch plan, or the traffic capacity of the existing section decreases by more than a first preset threshold; the reduction in the relevant equipment inventory of the target dispatch site exceeds a second preset threshold; the change in the geological risk value of the target substation exceeds a third preset threshold; wherein, the re-evaluation and generation includes re-executing the steps from determining candidate backup sites to generating the dispatch plan.

[0017] Secondly, this application provides a power grid emergency dispatching device, comprising:

[0018] The acquisition module is used to obtain the equipment requirement list in response to emergency dispatch trigger events for the target substation;

[0019] The first determination module is used to determine at least one candidate backup site based on the equipment requirement list, and to obtain the resource matching degree, importance index and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site.

[0020] The second determination module is used to determine the dispatch path distance from each candidate backup site to the target substation based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information.

[0021] The evaluation module is used to evaluate each candidate backup site based on scheduling path distance, resource matching degree, importance index, and correlation impact coefficient;

[0022] The scheduling scheme generation module is used to determine the target scheduling site from each candidate backup site and generate the corresponding scheduling scheme based on the evaluation results.

[0023] Thirdly, this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0024] Memory is used to store instructions executed by the computer;

[0025] A processor for executing computer-executable instructions stored in memory to implement any of the methods of the first aspect.

[0026] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed, are used to implement the method of any one of the first aspects.

[0027] Fifthly, this application provides a computer program product, including a computer program that, when executed, implements the method of any one of the first aspects.

[0028] The power grid emergency dispatching method, apparatus, equipment, and storage medium provided in this application, in response to an emergency dispatching trigger event targeting a target substation, obtains an equipment requirement list; based on the equipment requirement list, identifies at least one candidate backup site and obtains the resource matching degree, importance index, and correlation impact coefficient reflecting the cascading risk of the power grid for each candidate backup site; for each candidate backup site, determines the dispatching path distance from the candidate backup site to the target substation based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information; evaluates each candidate backup site based on the dispatching path distance, resource matching degree, importance index, and correlation impact coefficient; and, based on the evaluation results, determines the target dispatching site from among the candidate backup sites and generates a corresponding dispatching plan.

[0029] In this process, by planning feasible transportation routes based on dynamic road network data, the actual accessibility of material dispatch was ensured, improving the route failure problem caused by neglecting real-time weather and traffic control in traditional solutions, and significantly improving the timeliness of emergency response. Simultaneously, the correlation impact coefficient reflecting the cascading risks of the power grid was incorporated into a multi-dimensional evaluation system, proactively avoiding high-risk dispatching choices that could trigger cascading failures in decision-making, fundamentally strengthening the operational safety of the power grid in emergency situations. Furthermore, through automated and closed-loop process design, a comprehensive optimal dispatching plan can be generated within minutes, not only significantly shortening the time required for traditional manual dispatching, but also achieving technological breakthroughs in multiple dimensions such as precise resource matching and proactive risk prevention and control, fully meeting the comprehensive needs for efficiency, reliability, and safety in power emergency dispatching under disaster scenarios. Attached Figure Description

[0030] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0031] Figure 1 A flowchart illustrating a power grid emergency dispatch method provided as an exemplary embodiment of this application;

[0032] Figure 2 Another schematic diagram of the power grid emergency dispatch method provided as an exemplary embodiment of this application;

[0033] Figure 3 A schematic diagram of a power grid emergency dispatching device provided as an exemplary embodiment of this application;

[0034] Figure 4 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application.

[0035] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0036] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0037] The terms “first,” “second,” etc., used in the specification and claims of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented, for example, in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, products, or apparatus.

[0038] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0039] First, some of the terms used in this application will be explained:

[0040] Substation: refers to the core facility in a power system that performs voltage transformation and power distribution, including key equipment such as transformers and circuit breakers.

[0041] Equipment ledger: refers to a structured database that records the attributes (type, quantity, location, status) of equipment in a substation.

[0042] Main road closure: refers to the state in which the main road is closed to traffic due to disasters (such as landslides or flooding).

[0043] Site Importance: Priority coefficient (1.0-3.0) quantified based on substation power supply load and the scale of users covered. Among them, 3.0 corresponds to core hub substations (covering ≥100,000 users, power supply load ≥500MW), 2.0 corresponds to regional backbone substations (covering 30,000-100,000 users, power supply load 100-500MW), and 1.0 corresponds to ordinary distribution substations (covering <30,000 users, power supply load <100MW).

[0044] Impact of power loss: The risk coefficient (0-1) of a power grid cascading failure after a substation failure, where 0 indicates no cascading risk and 1 indicates extremely high cascading risk (which may lead to regional power grid collapse).

[0045] Geographic Information System (GIS): A technological system used to collect, store, manage, analyze, and display geospatial data.

[0046] Dijkstra's algorithm: a greedy algorithm for finding the shortest path from one node to all other nodes in a graph, widely used in the field of path planning.

[0047] MapReduce: A distributed computing model used to process large-scale datasets, which decomposes computing tasks into two parallel phases: Map and Reduce.

[0048] Structured models refer to models that process structured data (such as tabular data with fixed fields and formats), or models that have a clear structure (such as linear regression and decision trees). They are commonly used in data analysis, financial risk control, and other fields. They are suitable for processing data with clear logical relationships, such as numerical values ​​and categories. They rely on a predefined structure of data, have strong interpretability, but have low flexibility.

[0049] AutoGluon: An automated machine learning framework that automatically performs feature engineering, model selection, and hyperparameter tuning with just a few lines of code. It supports tabular, image, and text data, integrates with various models (such as XGBoost and neural networks), and is suitable for rapid prototyping.

[0050] DM Database: A relational database management system (RDBMS) that follows the common Structured Query Language (SQL) standard. This system supports atomicity, consistency, isolation, and durability of transactions, and is capable of handling high-concurrency requests and distributed architectures. Due to its advantages in data consistency, integrity, and security, it is often used in core business areas with stringent data management requirements.

[0051] Rule-based matching: This method processes data or makes decisions using predefined rules (not machine learning), such as regular expressions or conditional statements. It is suitable for simple, deterministic scenarios, such as text extraction and workflow approval. The rules are transparent and easy to maintain, but it is difficult to handle complex and ambiguous problems and requires manual rule writing.

[0052] Power Grid Management Platform: A system used to monitor, control, and optimize power system operation, record, and manage power grid equipment, assets, and operational data. It covers equipment parameters, maintenance records, defect management, fault information, etc., and supports full lifecycle management of equipment. This system interfaces with the power grid management platform to obtain data such as substation equipment parameters, power grid topology, and operating status.

[0053] Selenium is a widely used open-source automated testing framework primarily used for automated testing of World Wide Web (Web) applications. It automates testing by simulating user actions in a browser (clicks, input, and navigation, etc.). It supports cross-browser testing (such as Chrome, Firefox, Safari, etc.), ensuring webpage compatibility across different environments.

[0054] Traditional substation emergency material dispatching schemes heavily rely on manual experience and static information. Their standard procedures and inherent flaws are as follows: 1) In the resource matching phase, dispatchers must manually check equipment ledgers and contact each backup site by phone to verify inventory. This process is not only time-consuming (usually exceeding one hour), but also prone to resource misjudgment and ineffective dispatching due to delays in inventory information updates and human error. 2) In the route planning phase, general map software is typically used, relying solely on historical or static road network data. This mechanism cannot integrate real-time weather disasters (such as heavy rain and strong winds) causing road flooding and landslides, as well as real-time traffic control information issued by transportation departments. Therefore, in disaster scenarios, it is easy to plan "ghost routes" that are actually impassable, hindering repair teams and severely delaying rescue efforts. 3) In the final decision-making stage, traditional solutions typically rely solely on "nearest distance" as the core or sole decision-making criterion, neglecting two crucial dimensions: first, "site importance," which fails to differentiate the power supply priorities of core hub substations and ordinary distribution substations, potentially leading to delays in critical load restoration; and second, "grid topology interconnection risks," which fail to consider the cascading failure risks that may be triggered by dispatch operations, blindly transferring resources to sites with close electrical connections to the grid, which could amplify the scope of the fault and trigger a catastrophic grid cascading collapse. In summary, traditional solutions suffer from serious deficiencies in efficiency, feasibility, and safety: slow response, unreliable paths, short-sighted decision-making, and an inability to cope with complex and ever-changing disaster emergency scenarios.

[0055] While static scheduling schemes based on geographic information systems (GIS) can visualize equipment locations and rank candidate sites by distance, they still have fundamental limitations. First, at the data level, the scheme lacks a dynamic data fusion mechanism, making it unable to access and process real-time weather, geological disaster, and traffic control information. Consequently, its path planning is highly susceptible to failure during disasters. Second, at the decision-making level, its "distance-optimal" single-decision approach has serious flaws. It fails to incorporate "site importance," a key priority indicator reflecting the impact on power supply load and users, into its quantitative assessment, nor does it conduct any quantitative analysis of the cascading risks related to "voltage loss impact," which concerns the overall stability of the power grid. Therefore, these technical solutions can only achieve local approximate optimization in geographic space, and may make suboptimal or even dangerous scheduling decisions at the business logic and power grid security levels, failing to meet the core requirements of "efficiency" and "safety" in disaster scenarios.

[0056] To address the aforementioned issues, this application provides a power grid emergency dispatching scheme. After automatically sensing and responding to substation emergency events, it analyzes equipment requirements and accurately matches candidate sites that meet resource conditions, while simultaneously acquiring quantitative indicators reflecting their importance and power grid-related risks. Then, by dynamically fusing real-time meteorological and traffic control data, it determines the feasible transportation path distance for each candidate site under disaster conditions. Furthermore, it comprehensively evaluates and compares the determined actual path distance with the site's resource matching degree, importance, and power grid-related risk coefficient, thereby selecting the optimal target dispatching site and forming an executable dispatching scheme. This ensures that the emergency response is both efficient and rapid, while also fully considering and reducing the risks to power grid operation safety.

[0057] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0058] Figure 1 A flowchart illustrating a power grid emergency dispatching method provided as an exemplary embodiment of this application is shown. Figure 1 As shown, the power grid emergency dispatch method includes the following steps:

[0059] S101. In response to an emergency dispatch trigger event targeting the substation, obtain the equipment requirement list.

[0060] For example, when an emergency dispatch trigger event is detected for a target substation, the power grid management platform is accessed through the data interface to obtain data such as the equipment operating status and fault alarm information of the target substation. The type, specific model, and required quantity of equipment that needs to be repaired or replaced are then parsed to form a standardized equipment requirement list.

[0061] S102. Based on the equipment requirement list, identify at least one candidate backup site and obtain the resource matching degree, importance index and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site.

[0062] In some embodiments, determining at least one candidate backup site based on the equipment requirement list includes: defining a search range centered on the target substation according to a preset geographical search radius; and retrieving sites located within the search range and whose equipment inventory meets the equipment requirement list from a preset backup site database as candidate backup sites.

[0063] For example, taking the target substation as the center, a geographical search range is set (e.g., radius ≤ 300km). Combined with the equipment demand list, site information is retrieved from databases such as Dameng based on rule matching. Candidate backup sites that meet the criteria of "equipment type matching and minimum inventory level" are selected, along with key information such as the site name, equipment inventory quantity, three-dimensional coordinates, site importance level, and pressure loss correlation impact coefficient of the candidate backup sites.

[0064] Accordingly, for each candidate backup site identified, the resource matching degree is determined based on the quantity of its equipment inventory and the quantity of equipment required in the equipment demand list. For example, the ratio of the two quantities is used as the resource matching degree. The value of its site importance level is directly determined as its importance index. For example, the level values ​​preset in the database (such as 3.0 for core hub stations, 2.0 for regional backbone stations, and 1.0 for ordinary distribution stations) are the importance indexes. The value of its undervoltage correlation impact coefficient is determined as the correlation impact coefficient reflecting the grid cascading risk. The undervoltage correlation impact coefficient is a parameter pre-stored in the database that quantifies the grid cascading risk that the failure of the site may cause.

[0065] In one implementation, the prediction can be calculated using a power grid risk prediction model. This model is built using automated machine learning techniques, such as the AutoGluon framework, and trained using historical power grid fault data, such as historical fault case data from the past 5 years, to ensure its predictive reliability under different disaster scenarios (such as typhoons and rainstorms). The model's performance undergoes a rigorous validation process (such as using cross-validation) and achieves predetermined accuracy indicators (such as accuracy rate and F1 score). The model's input features include key parameters that reflect the power grid topology and operational safety risks, such as the electrical connection strength between the site and other key sites in the power grid (such as the load ratio of directly connected sites) and the estimated system performance loss (such as the total power transmission loss of the entire network). Based on these input features, the model outputs a quantified risk value within a predetermined range (such as between 0 and 1) through its internal calculation logic (which can be represented as a weighted combination or a more complex functional relationship). This is the aforementioned pressure loss correlation impact coefficient. For example, the calculation logic satisfies the formula: I_impact = α·(directly connected site load ratio) + β·(total network transmission power loss), where I_impact is the pressure loss correlation impact coefficient, and α and β are weight coefficients. These weight coefficients can be dynamically adjusted according to the growth of the model training data.

[0066] S103. For each candidate backup site, determine the dispatch path distance from the candidate backup site to the target substation based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information.

[0067] For example, two types of key dynamic information are acquired and integrated in real time: one is real-time meteorological monitoring data reflecting changes in the natural environment; the other is real-time traffic control data reflecting traffic conditions. Accordingly, based on previously stored historical road network data, the aforementioned real-time dynamic information is used as influencing factors to dynamically adjust and update the traffic attributes of each road segment in the road network, forming a dynamic road network model that reflects the current actual traffic capacity. In this model, real-time meteorological data mainly affects the traffic efficiency of road segments, while real-time traffic control data directly affects the passability of road segments. Furthermore, for each candidate backup site, based on this dynamic road network model, a path planning algorithm is used to calculate the best or optimal path from that site to the target substation under the current actual conditions. The physical length of this path is determined as the scheduling path distance used in subsequent evaluations.

[0068] S104. Evaluate each candidate backup site based on scheduling path distance, resource matching degree, importance index, and correlation influence coefficient.

[0069] For example, a comprehensive evaluation model with four independent dimensions is constructed, which evaluates each candidate backup site based on scheduling path distance, resource matching degree, importance index, and correlation influence coefficient. The scores converted from these four dimensions are then integrated and calculated according to a preset weighting scheme, ultimately calculating a quantitative comprehensive evaluation score for each candidate backup site. This comprehensive evaluation score can comprehensively reflect the site's overall performance in terms of timeliness, resources, importance, and security.

[0070] S105. Based on the evaluation results, determine the target scheduling site from each candidate backup site and generate the corresponding scheduling scheme.

[0071] For example, the comprehensive evaluation scores of all candidate backup sites are compared and ranked, and the site with the highest comprehensive evaluation score is determined as the final execution target for this emergency dispatch, i.e., the target dispatch site. This selection mechanism ensures that the selected site is the globally optimal solution after comprehensively weighing transportation efficiency, resource availability, site priority, and power grid security risks. Accordingly, based on the selection results, a detailed dispatch plan that can be executed immediately is automatically generated. This plan is complete and includes at least the following: 1) Execution entity information: clearly defined target dispatch site name, location, and contact information. 2) Resource allocation instructions: specific type, model, quantity, and technical status requirements of the equipment to be allocated. 3) Transportation action planning: a) Recommended transportation route: the currently feasible optimal transportation route calculated based on dynamic road network data; b) Key road condition information: marking bridges, tunnels, high-risk road sections, and real-time traffic precautions along the route; c) Estimated time nodes: providing segmented estimated travel time and total transportation time estimates. 4) Risk warning and guidance: providing safety risk warnings and suggested countermeasures during transportation, combined with real-time weather and road information.

[0072] Furthermore, a geographic information system (GIS) provides a visual representation of the scheduling process. This visualization includes a dual-path comparison view: based on a geographic base map, it overlays and compares normal reference paths planned from historical static road networks with actual feasible paths planned from dynamic road networks that integrate real-time disaster information. Differentiated visual styles (such as different colors and line types) are used to distinguish and identify the two paths. The view simultaneously labels the total distance and estimated travel time for each path, and highlights key road sections along the path (such as bridges, tunnels, and landslide-prone areas) and their impact from real-time disasters (such as rainfall and traffic control). This allows dispatchers to intuitively and quickly compare the feasibility and differences of paths under different options, helping them understand the basis for scheduling decisions and confirm the final transportation route.

[0073] The power grid emergency dispatch method provided in this application ensures the actual accessibility of material dispatch by planning feasible transportation routes based on dynamic road network data. This improves upon the path failure problem caused by neglecting real-time weather and traffic control in traditional solutions, significantly enhancing the timeliness of emergency response. Simultaneously, by incorporating the correlation impact coefficient reflecting power grid cascading risks into a multi-dimensional evaluation system, it proactively avoids high-risk dispatching choices that may trigger cascading failures during decision-making, fundamentally strengthening the operational safety of the power grid in emergency situations. Furthermore, through automated and closed-loop process design, it can generate a comprehensively optimal dispatching plan within minutes, not only significantly shortening the time required for traditional manual dispatching but also achieving technological breakthroughs in multiple dimensions such as precise resource matching and proactive risk prevention and control. This comprehensively meets the integrated requirements for efficiency, reliability, and safety in power emergency dispatching under disaster scenarios.

[0074] In some embodiments, the scheduling path distance from the candidate backup site to the target substation is determined based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information. This includes: acquiring real-time meteorological data and real-time traffic control information; determining the real-time meteorological impact factor of each road segment in the road network between the candidate backup site and the target substation based on the real-time meteorological data; determining the traffic control status of each road segment based on the real-time traffic control information; dynamically determining the traffic weight of each road segment in the dynamic road network data based on the basic length of each road segment, the corresponding real-time meteorological impact factor, and the traffic control status; and using a path planning algorithm to determine the shortest feasible path from the candidate backup site to the target substation based on the traffic weight of each road segment in the dynamic road network data, and determining the path length of the shortest feasible path as the scheduling path distance.

[0075] Real-time meteorological data, including precipitation intensity and wind speed, is collected through a sensor network deployed at substations and along the route. For real-time traffic control information, a dual update mechanism of "timed crawling + event triggering" is employed: under normal circumstances, automated testing tools (such as the Selenium framework) crawl the official websites of relevant transportation departments at fixed intervals (e.g., every 2 minutes); when a meteorological warning level reaches or exceeds a preset threshold (e.g., an orange warning), the crawling frequency is automatically increased to a higher level (e.g., every 30 seconds); simultaneously, a redundant backup channel is established with the application programming interface (API) of the relevant transportation department's official website; when webpage crawling fails, data can be immediately and seamlessly switched to the API interface, ensuring that the success rate of obtaining traffic control information is no less than, for example, 99.5%, providing a stable and timely data foundation for the construction of a dynamic road network model.

[0076] Accordingly, when determining the real-time meteorological influencing factors for each road segment, the specific values ​​are set based on a quantitative analysis of the correlation between meteorological conditions and road capacity. Specifically, by combining historical road traffic data of the areas where each road segment is located in the road network between the candidate backup site and the target substation (e.g., survey data on actual traffic capacity under different levels of severe weather in a certain area over the past 10 years), the impact of meteorological conditions such as precipitation intensity and wind force on road segment traffic efficiency (e.g., average vehicle speed, travel time) is statistically analyzed. For example, data analysis may reveal that under "heavy rain" level precipitation intensity, the actual traffic capacity of a road segment may decrease by 40% to 60% compared to clear weather. Based on such statistical analysis results, a quantitative mapping relationship from specific meteorological parameters (e.g., precipitation intensity mm / h, wind force) to traffic impact coefficients is established using data modeling methods (e.g., linear regression analysis). The final real-time meteorological impact factors for each road segment are determined based on this mapping relationship, dynamically looking up tables or calculating from real-time monitored meteorological data, thereby ensuring that the coefficient can accurately and scientifically reflect the actual impact of current meteorological conditions on the road network's traffic capacity.

[0077] Correspondingly, when determining the traffic control status of each road segment, the acquired traffic control information is converted into road segment-level labels, such as "permitted to pass" or "prohibited to pass".

[0078] Furthermore, based on the dynamically adjusted weights of the road network, the shortest path algorithm, such as Dijkstra's algorithm, is used to calculate the shortest feasible path from the candidate backup site to the target substation. The length of this path is the scheduling path distance.

[0079] This application embodiment quantifies real-time meteorological data into meteorological impact factors for each road segment and converts traffic control information into road segment traffic status, thereby constructing a dynamic road network that accurately reflects the current road capacity and interruption status. Based on this, the traffic weight of each road segment is dynamically adjusted according to its basic length, meteorological impact, and control status. A path planning algorithm is then used to calculate the shortest feasible path based on these weights. This ensures that the planned transportation path is not based on static or outdated information, but fully considers the actual impact of meteorological disasters such as rainstorms and strong winds on road traffic efficiency. It also effectively avoids road segments that are actually closed due to landslides, flooding, or traffic control, thus fundamentally improving the problem of "planned path infeasibility" under disaster conditions. The final output dispatch path distance is a real, reliable, and executable transportation distance under the current environment, providing a solid and effective input for subsequent dispatch decisions and significantly improving the feasibility and timeliness of emergency dispatch plans.

[0080] In some embodiments, the real-time meteorological impact factor includes precipitation coefficient and wind force coefficient. Based on the basic length of each road segment, the corresponding real-time meteorological impact factor, and the traffic control status, the traffic weight of each road segment in the dynamic road network data is dynamically determined, including: for the first road segment marked as prohibited from passage under traffic control status, the traffic weight of the first road segment is set to infinity or a preset maximum value; for the second road segment marked as permitted from passage under traffic control status, a meteorological impact adjustment coefficient is determined based on the precipitation coefficient and wind force coefficient of the second road segment, and the product of the basic length of the second road segment and the meteorological impact adjustment coefficient is used as the traffic weight of the second road segment in the dynamic road network data.

[0081] For example, when converting meteorological data into quantified impact coefficients, this specifically involves mapping precipitation intensity to precipitation coefficients, such as a coefficient of 0.1 for light rain (1-10 mm / h), a coefficient of 0.3 for moderate rain (10-25 mm / h), a coefficient of 0.5 for heavy rain (25-50 mm / h), and a coefficient of 0.8 for torrential rain (≥50 mm / h); and mapping wind force level to wind force coefficients, such as a coefficient of 0.1 for winds of force 3-4, a coefficient of 0.3 for winds of force 5-6, a coefficient of 0.6 for winds of force 7-8, and a coefficient of 0.9 for winds of force 9 and above.

[0082] Accordingly, for road sections marked "No Entry" (e.g., closed due to landslides, flooding, or traffic control), their passage weight is set to "infinity" or a maximum value much larger than the weight of normal road sections to ensure that the road section will not be selected in the path planning algorithm. For road sections marked "Allow Entry," the dynamic weight is determined as follows: 1) Calculation of meteorological impact adjustment coefficient: The precipitation coefficient and wind force coefficient of the road section are calculated according to a preset weighting formula. For example, the meteorological impact adjustment coefficient = 1 + w_p × precipitation coefficient + w_w × wind force coefficient, where the values ​​of the weighting factors w_p and w_w (e.g., w_p = 0.3, w_w = 0.2) are determined based on statistical analysis (e.g., through linear regression analysis) of the impact of different meteorological factors on road traffic efficiency under historical severe weather conditions to ensure that the coefficients can truly reflect the quantitative impact of meteorological conditions on road network traffic. 2) The traffic weight of this road segment is determined by multiplying the "basic length of the road segment" by the "weather impact adjustment coefficient", that is, traffic weight = basic length × weather impact adjustment coefficient. This means that under severe weather conditions, the "effective traffic distance" of the road segment will be dynamically extended due to the decrease in its traffic capacity.

[0083] In this embodiment, for road sections marked as "no passage" by traffic control, the weight of these sections is set to infinity or a maximum value. This algorithm avoids these impassable sections, fundamentally reducing the safety hazard of "leading to dead ends" that traditional planning might create, and ensuring the underlying feasibility of the scheduling plan. Secondly, for road sections that are passable, a meteorological impact adjustment coefficient is calculated and multiplied by the basic length of the road section. This achieves a precise conversion of the impact of meteorological disasters from a qualitative description to a quantitative cost, enabling the route planning algorithm to dynamically balance detour distance and traffic efficiency under severe weather conditions. This allows for the planning of the most cost-effective transportation route under actual weather conditions. This differentiated weighting strategy not only ensures the absolute passability of the route but also maximizes transportation efficiency in disaster environments through the scientific quantification of the passability of road sections. This provides a reliable distance basis for subsequent scheduling decisions, significantly improving the reliability and timeliness of emergency response plans.

[0084] In some embodiments, each candidate backup site is evaluated based on scheduling path distance, resource matching degree, importance index, and correlation impact coefficient. This includes: determining an accessibility score based on scheduling path distance (the shorter the scheduling path distance, the higher the accessibility score); determining a resource score based on resource matching degree (the higher the resource matching degree, the higher the resource score); determining an importance score based on importance index (the higher the importance index, the higher the importance score); determining a security score based on correlation impact coefficient (the lower the grid cascading risk represented by the correlation impact coefficient, the higher the security score); and then weighted summing the accessibility score, resource score, importance score, and security score to obtain the evaluation result of the candidate backup site.

[0085] Accordingly, according to the preset scoring rules, independent scores in four dimensions are calculated for each candidate backup site. For example, Table 1 is an example of the scoring rules provided by the exemplary embodiment of this application.

[0086]

[0087] Correspondingly, the comprehensive evaluation score of the candidate backup site satisfies the following formula: Score = (Accessibility score × ... ) + (Resource matching score × ) + (Site Importance Score × ) + (Relevance Impact Score × ).in, and The weights for each dimension are determined based on expert research and the Analytic Hierarchy Process (AHP) in the field of power emergency dispatch. The specific allocation is as follows: 1) Spatial accessibility dimension weights ( 1) 30%, assigned the highest weight to prioritize the timeliness of emergency dispatch; 2) Resource dimension weight ( ): 25%, ensuring the effectiveness of the scheduling plan at the resource level; 3) Site importance dimension weight ( ): 20%, taking into account the power supply priority of the site in the power grid; 4) Security dimension weight ( ): 25%, assigning a weight commensurate with the resource dimension to effectively control grid cascading risks.

[0088] Correspondingly, substituting the specific scoring rules and weights mentioned above, we get: Score = (1 / D_real) × 30% + (N_ratio) × 25% + (S_level / 3.0) × 20% + (1 - I_impact) × 25%.

[0089] In some embodiments, to meet the stringent timeliness requirements of emergency dispatch, a distributed parallel computing architecture is employed to improve processing efficiency when calculating the comprehensive evaluation score of each candidate backup site. Specifically, big data parallel computing frameworks such as MapReduce can be used to decompose the scoring calculation task for multiple candidate sites into multiple parallel executable subtasks. These subtasks are distributed to different nodes of the computing cluster for simultaneous execution, each independently completing the scoring calculation and weighted summation of each dimension for the specified site, and finally quickly summarizing and sorting all the results. Through this parallel computing approach, the overall evaluation time for a large-scale candidate site set can be significantly shortened, ensuring that the response time for the entire process from triggering the evaluation to generating the scoring results for all sites is less than, for example, 3 seconds, thus providing crucial performance guarantees for minute-level end-to-end dispatch decisions.

[0090] Furthermore, based on the comprehensive evaluation scores of each candidate backup site, a candidate evaluation result is generated. This evaluation result not only includes the comprehensive evaluation score of each site, but also clearly displays the core parameters and intermediate results of each dimension in the decision dashboard. For example, Table 2 provides an example of the core information and comprehensive evaluation scores of each candidate backup site provided in the exemplary embodiment of this application.

[0091]

[0092] It should be noted that the weights of each dimension shown in Table 1 (such as spatial accessibility 30%, resource sufficiency 25%), and the specific parameter values ​​of each candidate site in the example in Table 2 (such as basic distance, scheduling path distance, resource matching degree, etc.) are all specific examples based on a particular implementation or simulated scenario. In actual applications or different implementation methods, the weight allocation of each dimension can be dynamically configured and optimized according to specific scheduling strategies, expert experience, or broader AHP analysis results; at the same time, the actual parameters of each candidate site (path distance, inventory status, risk coefficient, etc.) will also change with the changes in real-time data. No limitations are made here regarding the weights of each dimension shown in Table 1 and the specific parameter values ​​of each candidate site in the example in Table 2.

[0093] This application embodiment achieves a scientific and comprehensive evaluation of candidate backup sites by systematically integrating four key factors: transportation efficiency, resource security, site priority, and power grid security. Based on the core objectives of power grid emergency dispatch and expert experience, a weighted comprehensive evaluation score is generated through preset weights. This evaluation mechanism effectively overcomes the blindness of traditional "nearest distance" single-choice decisions, ensuring that selected target dispatch sites not only have relatively efficient material transportation routes but also sufficient resource security, high power restoration priority, and low risk of triggering cascading failures. This fundamentally achieves the optimal balance between dispatch efficiency and power grid operation safety. Furthermore, by generating a visual decision dashboard containing core parameters of each dimension and the final score, the evaluation process and results are made transparent and intuitive. This greatly assists dispatchers in quickly understanding the decision-making basis, comparing the advantages and disadvantages of each site, and ultimately making a globally optimal dispatch decision that balances timeliness, reliability, and security, significantly improving the scientific nature, interpretability, and overall effectiveness of emergency response decisions.

[0094] In some embodiments, the emergency dispatch trigger event is triggered in the following manner: continuously monitoring the geological risk value of the target substation; when the geological risk value is detected to be greater than or equal to a preset risk trigger threshold, an emergency dispatch trigger event is determined to have occurred; wherein, the geological risk value is determined based on real-time precipitation data, real-time wind data, and geological topography data of the area where the target substation is located.

[0095] For example, a sensor network deployed around and in the area surrounding a substation continuously collects real-time precipitation and wind data, which serves as the core dynamic input for calculating geological risk values. This data is then integrated with the power grid management platform and pre-set databases or relevant geographic information databases to obtain information including substation equipment records (equipment type, model, location coordinates, and affiliated site), standby site information (site name, 3D coordinates, power supply range, importance level, etc.), power grid topology data (connections between substations, transmission line parameters, etc.), and static or semi-static background information such as the topographic features and geological stability of the substation area. The collected raw data is then cleaned, integrated, and quantified. For instance, invalid data (such as incorrectly formatted coordinate data or duplicate inventory records) is removed, missing data is supplemented using interpolation, meteorological data is converted into corresponding precipitation and wind coefficients, qualitative indicators such as site importance and pressure loss impact are converted into quantitative coefficients, and traffic control information is converted into closed road segment weights (with the closed road segment weight set to a maximum value, indicating impassable access). This provides standardized data for subsequent decision-making. Accordingly, the real-time precipitation data, real-time wind data, and geological and topographic data obtained above are integrated. Specifically, a pre-set quantitative analysis model (such as a weighted scoring method) is used to comprehensively consider the impact of precipitation intensity and wind level on surface stability, and combined with the inherent geological vulnerability of the region, to determine a comprehensive geological risk value. This risk value is used to quantitatively characterize the level at which the substation is prone to secondary geological disasters (such as landslides and debris flows affecting site safety) or increased equipment operation risks due to current meteorological conditions.

[0096] Accordingly, the geological risk value of the target substation is continuously and automatically monitored and updated. When the geological risk value of the target substation is detected to be greater than or equal to the preset risk trigger threshold, the system immediately and automatically determines that the current situation has reached the emergency response standard, and then generates a clear emergency dispatch trigger event signal. This event signal will be automatically transmitted to subsequent processes, serving as a unified and standardized starting point for initiating the entire emergency material dispatch decision-making process, thereby triggering a series of subsequent operations such as obtaining the equipment requirement list. The preset risk trigger threshold is a pre-assessed risk trigger threshold (e.g., set to 6 based on historical data and expert experience), representing the critical risk level at which the system determines that emergency dispatch intervention is necessary.

[0097] This application's embodiments fundamentally change the traditional passive mode of emergency dispatch, which relies on manual alarms or simple alerts, by fusing multi-source environmental data into a quantifiable risk indicator and setting a clear trigger threshold. This enables proactive and accurate perception of potential risks to power grid infrastructure, automatically determining and initiating emergency response procedures before disasters (such as heavy rainfall and strong winds) pose a substantial threat to substations. This significantly advances the starting point for emergency decision-making from "a fault has occurred" to "a high risk is imminent," providing valuable preparation time for subsequent key decision-making stages such as resource matching and path planning, and significantly shortening the overall response delay from the emergence of risk to the mobilization of repair resources. Simultaneously, because the triggering criteria are objective and standardized, it reduces the problem of untimely response caused by delays in manual judgment or inconsistent standards, thereby comprehensively improving the power grid's proactive defense capabilities and emergency response efficiency in extreme weather and other disaster scenarios, gaining a competitive advantage in ensuring power supply security.

[0098] Based on the above embodiments, in some embodiments, the power grid emergency dispatch method further includes a dynamic correction step for the dispatch plan: after generating the dispatch plan, continuously monitor real-time meteorological data, real-time traffic control information, and the equipment inventory status of each candidate backup site; when any of the following dynamic change events are detected, trigger the re-evaluation and generation of the dispatch plan: a new traffic control section is added to the transportation path corresponding to the dispatch plan, or the traffic capacity of the existing section decreases by more than a first preset threshold; the reduction in the relevant equipment inventory of the target dispatch site exceeds a second preset threshold; the change in the geological risk value of the target substation exceeds a third preset threshold; wherein, the re-evaluation and generation includes re-executing the steps from determining candidate backup sites to generating the dispatch plan.

[0099] For example, after generating the scheduling plan, a data update is automatically performed at fixed short intervals (e.g., every 5 minutes) to obtain the latest real-time weather data, real-time traffic control information, and equipment inventory status of each candidate backup site. After each data update, the latest data is compared in real time with the data benchmark on which the original scheduling plan was based. When any of the following quantitative change events are detected, the effectiveness of the original scheduling plan is automatically determined to be compromised, and a correction process is immediately triggered:

[0100] 1) Deterioration of traffic conditions on the transportation route: New traffic control sections appear in the transportation route corresponding to the scheduling plan; or, the traffic capacity of the existing road sections in the route decreases by a value that reaches or exceeds the first preset threshold (e.g., traffic efficiency decreases by ≥30%).

[0101] 2) Target site resource guarantee gap: In the target scheduling site, the reduction in equipment inventory related to the equipment demand list reaches or exceeds the second preset threshold (e.g., inventory reduction ≥10%), or the inventory quantity drops to zero.

[0102] 3) Dramatic change in the risk status of the target substation: The geological risk value of the target substation changes by a magnitude that reaches or exceeds the third preset threshold (e.g., risk value fluctuation ≥ 1.5).

[0103] Correspondingly, after the correction is triggered, the correction operation is executed according to the preset priority logic. The specific process is as follows: 1) Local resource verification and path recalculation: Verify whether there are alternative resources (e.g., other available batches of the same model) within the original target dispatching site that meet the equipment requirement list. If so, the dispatching path distance from the site to the target substation is recalculated based solely on the updated real-time meteorological data and traffic control information. The transportation path and estimated time are updated accordingly, and a corrected dispatching plan is generated. 2) If the first step verifies that there are no sufficient alternative resources at the original target dispatching site, the complete re-evaluation process is executed. This involves restarting all steps from "determining at least one candidate backup site based on the equipment requirement list" to "generating the corresponding dispatching plan." Based on the latest global data, the optimal target dispatching site is reselected, and a new dispatching plan is generated. In the entire dynamic correction process, from the fulfillment of the triggering conditions to the generation of a new or corrected executable dispatching plan, the total time does not exceed 2 minutes, effectively ensuring that the dispatching plan can maintain a high degree of real-time performance and effectiveness in rapidly changing disaster environments.

[0104] This application's embodiment introduces a dynamic correction mechanism for the scheduling scheme. After the scheduling scheme is generated, it continuously tracks three core dynamic factors: the real-time traffic status of the transportation route, changes in resource inventory at the target site, and the risk evolution of the target substation itself. Once any factor is detected to have a significant change exceeding a preset threshold (such as a newly added route closure, substantial inventory depletion, or a sharp increase in risk), the scheduling scheme is automatically re-evaluated and generated. This effectively solves the pain point of traditional static schemes rapidly failing under rapidly changing disaster environments, ensuring that scheduling instructions can respond in real time to emergencies such as road interruptions, resource occupation, and escalating on-site risks. It reduces the possibility of directing transport vehicles to closed sections or sites with no inventory due to information delays. By using dynamic correction as a standard process, it effectively ensures that the output scheduling scheme is not only optimal at the time of generation but also maintains high feasibility and security throughout the subsequent execution window, thereby significantly improving the reliability, success rate, and anti-interference capability of the entire emergency response process.

[0105] Figure 2 Another schematic diagram of the power grid emergency dispatch method provided for an exemplary embodiment of this application. (See diagram below.) Figure 2 As shown, the power grid emergency dispatch method includes the following steps:

[0106] S201. Obtain the geological risk value of the target substation.

[0107] S202. Determine whether the geological risk value is greater than or equal to the preset risk trigger threshold.

[0108] If so, execute S203;

[0109] If not, proceed with S201.

[0110] S203. Determine if an emergency dispatch trigger event has occurred and obtain the equipment requirement list.

[0111] S204. Based on the equipment requirement list, with the target substation as the center, the search range is defined according to the preset geographical search radius. Sites located within the search range and whose equipment inventory meets the equipment requirement list are retrieved from the preset backup site database as candidate backup sites. There is at least one candidate backup site.

[0112] S205. Obtain the resource matching degree, importance index, and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site.

[0113] S206. For each candidate backup site, determine the dispatch path distance from the candidate backup site to the target substation based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information.

[0114] In some embodiments, the scheduling path distance from the candidate backup site to the target substation is determined based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information. This includes: acquiring real-time meteorological data and real-time traffic control information; determining the real-time meteorological impact factor of each road segment in the road network between the candidate backup site and the target substation based on the real-time meteorological data; determining the traffic control status of each road segment based on the real-time traffic control information; dynamically determining the traffic weight of each road segment in the dynamic road network data based on the basic length of each road segment, the corresponding real-time meteorological impact factor, and the traffic control status; and using a path planning algorithm to determine the shortest feasible path from the candidate backup site to the target substation based on the traffic weight of each road segment in the dynamic road network data, and determining the path length of the shortest feasible path as the scheduling path distance.

[0115] S207. Each candidate backup site is evaluated based on scheduling path distance, resource matching degree, importance index, and correlation influence coefficient.

[0116] In some embodiments, each candidate backup site is evaluated based on scheduling path distance, resource matching degree, importance index, and correlation impact coefficient. This includes: determining an accessibility score based on scheduling path distance (the shorter the scheduling path distance, the higher the accessibility score); determining a resource score based on resource matching degree (the higher the resource matching degree, the higher the resource score); determining an importance score based on importance index (the higher the importance index, the higher the importance score); determining a security score based on correlation impact coefficient (the lower the grid cascading risk represented by the correlation impact coefficient, the higher the security score); and then weighted summing the accessibility score, resource score, importance score, and security score to obtain the evaluation result of the candidate backup site.

[0117] S208. Based on the evaluation results, determine the target scheduling site from each candidate backup site and generate the corresponding scheduling scheme.

[0118] S209. Continuously monitor real-time meteorological data, real-time traffic control information, and equipment inventory status of each candidate backup site. When a preset dynamic change event is detected, a re-evaluation and generation of the scheduling plan is triggered.

[0119] The preset dynamic change events include: the addition of traffic control sections in the transportation route corresponding to the scheduling plan, or the decrease in the traffic capacity of existing sections exceeding the first preset threshold; the reduction in the relevant equipment inventory of the target scheduling site exceeding the second preset threshold; and the change in the geological risk value of the target substation exceeding the third preset threshold. The reassessment and generation includes re-executing the steps from determining candidate backup sites to generating the scheduling plan.

[0120] In summary, this application has at least the following advantages:

[0121] First, by establishing a complete automated process from automatic geological risk triggering and real-time multi-source data collection to intelligent assessment based on dynamic road network and four-dimensional decision-making, and then to distributed parallel computing, the traditional scheduling and decision-making process, which relies on human experience and takes more than 1 hour, is compressed to less than 10 minutes, resulting in an overall efficiency improvement of more than 80%. This has won valuable "golden time" for disaster relief and greatly improved the emergency response capability of the power system.

[0122] Second, by quantifying the cascading risk of "power outage impact" and incorporating it as a key dimension into dispatching decisions, and by quantitatively assessing the cascading failure risks that dispatching each candidate site may trigger, high-risk selections can be proactively avoided, reducing the risk of cascading failures by, for example, more than 40%. This mechanism fundamentally changes the previous shortcomings of dispatching that "emphasized distance and neglected safety," placing the overall stability of the power grid at the core of decision-making and significantly enhancing the safety of emergency operations.

[0123] Third, through a multi-dimensional precise matching mechanism (including spatial accessibility, resource matching degree, site importance and power grid security), the optimal connection between the demand of faulty equipment and backup resources is achieved, with an equipment matching accuracy rate of, for example, over 98%. This not only reduces ineffective scheduling and resource waste caused by inaccurate information and lowers emergency costs, but also ensures that the scheduled resources can meet the actual needs of on-site emergency repairs to the greatest extent.

[0124] Fourth, by constructing a complete closed loop of "perception-decision-execution-verification," the system continuously updates environmental and resource data every 5 minutes and sets clear dynamic correction trigger conditions. Once the traffic conditions of the transportation route deteriorate, the inventory at the target site is insufficient, or the on-site risks change drastically, the system can quickly initiate a local or global re-decision process within, for example, 2 minutes. This ensures that the generated scheduling plan can adapt to external changes in real time and always maintain a high degree of feasibility and timeliness, effectively overcoming the inherent defect of static plans rapidly failing in dynamic disaster scenarios.

[0125] Fifth, by leveraging a geographic information system to provide visualized outputs such as dual-path comparisons and decision dashboards, dispatchers can intuitively compare the differences between various options and clearly understand the merits and justifications of each candidate site. This not only significantly reduces the difficulty of understanding and executing dispatch instructions and improves human-machine collaboration efficiency, but also provides clear and complete data support for post-event analysis and optimization.

[0126] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0127] Figure 3 A schematic diagram of a power grid emergency dispatching device provided as an exemplary embodiment of this application. (See diagram below.) Figure 3 As shown, the power grid emergency dispatching device 30 includes an acquisition module 31, a first determination module 32, a second determination module 33, an evaluation module 34, and a dispatching scheme generation module 35, wherein:

[0128] The acquisition module 31 is used to acquire the equipment requirement list in response to an emergency dispatch trigger event for the target substation;

[0129] The first determination module 32 is used to determine at least one candidate backup site based on the equipment requirement list, and to obtain the resource matching degree, importance index and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site;

[0130] The second determining module 33 is used to determine the dispatch path distance from the candidate backup site to the target substation for each candidate backup site based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information.

[0131] Evaluation module 34 is used to evaluate each candidate backup site based on scheduling path distance, resource matching degree, importance index and correlation impact coefficient;

[0132] The scheduling scheme generation module 35 is used to determine the target scheduling site from each candidate backup site and generate the corresponding scheduling scheme based on the evaluation results.

[0133] In one possible implementation, the second determining module 33 may be specifically used to: acquire real-time meteorological data and real-time traffic control information; determine the real-time meteorological impact factors of each road segment in the road network between the candidate backup site and the target substation based on the real-time meteorological data; determine the traffic control status of each road segment based on the real-time traffic control information; dynamically determine the traffic weight of each road segment in the dynamic road network data according to the basic length of each road segment, the corresponding real-time meteorological impact factors, and the traffic control status; and determine the shortest feasible path from the candidate backup site to the target substation using a path planning algorithm based on the traffic weight of each road segment in the dynamic road network data, and determine the path length of the shortest feasible path as the scheduling path distance.

[0134] In one possible implementation, the real-time meteorological impact factor includes precipitation coefficient and wind force coefficient. The second determining module 33 can also be used to: for a first road segment marked as prohibited from passage under traffic control status, set the passage weight of the first road segment to infinity or a preset maximum value; for a second road segment marked as permitted from passage under traffic control status, determine the meteorological impact adjustment coefficient based on the precipitation coefficient and wind force coefficient of the second road segment, and use the product of the basic length of the second road segment and the meteorological impact adjustment coefficient as the passage weight of the second road segment in the dynamic road network data.

[0135] In one possible implementation, the evaluation module 34 can be specifically used to: determine an accessibility score based on the scheduling path distance, where a shorter scheduling path distance results in a higher accessibility score; determine a resource score based on resource matching degree, where a higher resource matching degree results in a higher resource score; determine an importance score based on an importance index, where a higher importance index results in a higher importance score; determine a security score based on the correlation impact coefficient, where a lower correlation impact coefficient indicates a lower power grid cascading risk, resulting in a higher security score; and perform a weighted summation of the accessibility score, resource score, importance score, and security score to obtain the evaluation result of the candidate backup site.

[0136] In one possible implementation, the emergency dispatch trigger event is triggered by continuously monitoring the geological risk value of the target substation; when the geological risk value is greater than or equal to a preset risk trigger threshold, an emergency dispatch trigger event is determined to have occurred; wherein, the geological risk value is determined based on real-time precipitation data, real-time wind data, and geological topography data of the area where the target substation is located.

[0137] In one possible implementation, the first determining module 32 may be specifically used to: define a search range centered on the target substation according to a preset geographical search radius; and retrieve from a preset backup site database sites located within the search range and whose equipment inventory meets the equipment demand list as candidate backup sites.

[0138] In one possible implementation, the scheduling scheme generation module 35 can be specifically used to: continuously monitor real-time meteorological data, real-time traffic control information, and the equipment inventory status of each candidate backup site after generating the scheduling scheme; when any of the following dynamic change events are detected, trigger the re-evaluation and generation of the scheduling scheme: a new traffic control section is added to the transportation route corresponding to the scheduling scheme, or the traffic capacity of the existing section decreases by more than a first preset threshold; the reduction in the relevant equipment inventory of the target scheduling site exceeds a second preset threshold; the change in the geological risk value of the target substation exceeds a third preset threshold; wherein, the re-evaluation and generation includes re-executing the steps from determining candidate backup sites to generating the scheduling scheme.

[0139] The power grid emergency dispatching device provided in this application embodiment can execute the technical solution shown in the above power grid emergency dispatching method embodiment. Its implementation principle and beneficial effects are similar, and will not be repeated here.

[0140] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0141] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0142] It should be noted that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways; and it should be understood that the division of the various modules of the above device is only a logical functional division, and in actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can all be implemented in software through processing element calls; they can all be implemented in hardware; or some modules can be implemented by processing element calls to software, and some modules can be implemented in hardware. For example, the evaluation module can be a separately established processing element, or it can be integrated into a chip of the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element of the above device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the integrated logic circuit in the hardware of the processor element or by software instructions.

[0143] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-On-a-Chip (SOC).

[0144] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Video Discs, DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0145] Figure 4 A schematic diagram of the structure of an electronic device provided as an exemplary embodiment of this application. For example... Figure 4 As shown, the electronic device 40 in this embodiment includes:

[0146] At least one processor 41; and a memory 42 communicatively connected to the at least one processor;

[0147] The memory 42 stores instructions that can be executed by at least one processor 41 to cause the electronic device to perform the method as described in any of the above embodiments.

[0148] Alternatively, the memory 42 can be either standalone or integrated with the processor 41.

[0149] The memory 42 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0150] The processor 41 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application. Specifically, when implementing the power grid emergency dispatch method described in the foregoing method embodiments, the electronic device may be, for example, an electronic device with processing capabilities such as a server.

[0151] Optionally, the electronic device may also include a communication interface 43. In specific implementations, if the communication interface 43, memory 42, and processor 41 are implemented independently, they can be interconnected via a bus to complete communication. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc., but this does not imply that there is only one bus or one type of bus.

[0152] Optionally, in a specific implementation, if the communication interface 43, memory 42 and processor 41 are integrated on a single chip, then the communication interface 43, memory 42 and processor 41 can communicate through an internal interface.

[0153] The implementation principle and technical effects of the electronic device provided in this embodiment can be found in the foregoing embodiments, and will not be repeated here.

[0154] This application also provides a computer-readable storage medium storing computer-executable instructions. When the computer-executable instructions are executed, they are used to implement the method steps as described in the above method embodiments. The specific implementation methods and technical effects are similar, and will not be repeated here.

[0155] The aforementioned computer-readable storage media can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0156] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in a power grid emergency dispatching device.

[0157] This application also provides a computer program product, including a computer program, which, when executed, implements the method steps as described in the above method embodiments. The specific implementation and technical effects are similar and will not be repeated here.

[0158] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as the combination of these technical features does not contradict each other, it should be considered within the scope of this specification.

[0159] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0160] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A power grid emergency dispatch method, characterized in that, include: In response to emergency dispatch events triggered for the target substation, obtain a list of equipment requirements; Based on the equipment requirement list, at least one candidate backup site is identified, and the resource matching degree, importance index, and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site are obtained. For each of the candidate backup sites, the dispatch path distance from the candidate backup site to the target substation is determined based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information. Each candidate backup site is evaluated based on the scheduling path distance, the resource matching degree, the importance index, and the correlation influence coefficient. Based on the evaluation results, the target scheduling site is determined from each of the candidate backup sites, and the corresponding scheduling scheme is generated.

2. The power grid emergency dispatching method according to claim 1, characterized in that, The step of determining the dispatch path distance from the candidate backup site to the target substation based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information includes: Obtain real-time weather data and real-time traffic control information; Based on the real-time meteorological data, the real-time meteorological influence factors of each road segment in the road network between the candidate backup site and the target substation are determined. Based on the real-time traffic control information, the traffic control status of each road segment is determined; Based on the basic length of each road segment, the corresponding real-time meteorological influence factors, and the traffic control status, the traffic weight of each road segment in the dynamic road network data is dynamically determined. Based on the traffic weight of each road segment in the dynamic road network data, a path planning algorithm is used to determine the shortest feasible path from the candidate backup site to the target substation, and the path length of the shortest feasible path is determined as the scheduling path distance.

3. The power grid emergency dispatching method according to claim 2, characterized in that, The real-time meteorological influencing factors include precipitation coefficient and wind force coefficient. The dynamic determination of the traffic weight of each road segment in the dynamic road network data, based on the basic length of each road segment, the corresponding real-time meteorological influencing factors, and traffic control status, includes: For the first road segment marked as prohibited from passage under traffic control status, the traffic weight of the first road segment is set to infinity or a preset maximum value; For the second road segment marked as permitted by traffic control status, a meteorological impact adjustment coefficient is determined based on the precipitation coefficient and wind force coefficient of the second road segment, and the product of the basic length of the second road segment and the meteorological impact adjustment coefficient is used as the traffic weight of the second road segment in the dynamic road network data.

4. The power grid emergency dispatching method according to claim 1, characterized in that, The evaluation of each candidate backup site based on the scheduling path distance, resource matching degree, importance index, and correlation influence coefficient includes: The reachability score is determined based on the scheduling path distance; the shorter the scheduling path distance, the higher the reachability score. A resource score is determined based on the resource matching degree; the higher the resource matching degree, the higher the resource score. An importance score is determined based on the importance index; the higher the importance index, the higher the importance score. The safety score is determined based on the correlation influence coefficient. The lower the power grid cascading risk represented by the correlation influence coefficient, the higher the safety score. The evaluation result of the candidate backup site is obtained by weighting and summing the reachability score, the resource score, the importance score and the security score.

5. The power grid emergency dispatch method according to any one of claims 1 to 4, characterized in that, The emergency dispatch trigger event is triggered in the following way: Continuously monitor the geological risk value of the target substation; When the geological risk value is detected to be greater than or equal to the preset risk trigger threshold, it is determined that the emergency dispatch trigger event has occurred; The geological risk value is determined based on real-time precipitation data, real-time wind data, and geological and topographical data of the area where the target substation is located.

6. The power grid emergency dispatching method according to any one of claims 1 to 4, characterized in that, The step of determining at least one candidate backup site based on the equipment requirement list includes: Centered on the target substation, the search range is defined according to the preset geographical search radius; Sites within the preset backup site database that are within the search range and whose equipment inventory meets the equipment demand list are selected as candidate backup sites.

7. The power grid emergency dispatching method according to any one of claims 1 to 4, characterized in that, It also includes a dynamic adjustment step for the scheduling scheme: After generating the scheduling plan, the real-time meteorological data, real-time traffic control information, and equipment inventory status of each candidate backup site are continuously monitored. The scheduling scheme will be re-evaluated and regenerated when any of the following dynamic change events are detected: The dispatching scheme includes newly added traffic control sections in the transportation route, or the traffic capacity of existing sections decreases by more than the first preset threshold. The reduction in the relevant equipment inventory at the target scheduling site exceeds the second preset threshold. The geological risk value of the target substation changes beyond a third preset threshold. The re-evaluation and generation includes re-executing the steps from determining candidate backup sites to generating a scheduling scheme.

8. A power grid emergency dispatching device, characterized in that, include: The acquisition module is used to obtain the equipment requirement list in response to emergency dispatch trigger events for the target substation; The first determining module is used to determine at least one candidate backup site based on the equipment requirement list, and to obtain the resource matching degree, importance index and correlation impact coefficient reflecting the grid cascading risk of each candidate backup site; The second determining module is used to determine the dispatch path distance from the candidate backup site to the target substation for each candidate backup site based on dynamic road network data that integrates real-time meteorological data and real-time traffic control information. The evaluation module is used to evaluate each of the candidate backup sites based on the scheduling path distance, the resource matching degree, the importance index, and the correlation influence coefficient. The scheduling scheme generation module is used to determine the target scheduling site from each of the candidate backup sites and generate the corresponding scheduling scheme based on the evaluation results.

9. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory is used to store computer-executed instructions; The processor is configured to execute the computer execution instructions to implement the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed, are used to implement the method as described in any one of claims 1 to 7.

Images