Power grid operation and maintenance method and device, computer equipment and readable storage medium

Abstract

The application relates to a power grid operation and maintenance method and device, computer equipment and a readable storage medium. The method comprises the following steps: determining a plurality of operation and maintenance tasks of a power grid, an association relationship between any two operation and maintenance tasks, a task graph, and determining a conflict edge and a dependent edge to which a node belongs in the task graph; for the conflict edge to which the node belongs, the conflict strength of the node in the task graph is obtained based on the overlapping degree of the work area between the node and another node on the conflict edge and the overlapping degree of the work period; and the operation and maintenance tasks allocated by the agent are adjusted based on the path length of the shortest passage path between the work area of the agent and the operation and maintenance task, the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the agent, the conflict strength and the importance degree value of the dependent edge. The method provided by the application can effectively improve the operation and maintenance efficiency of the power grid.

Description

Technical Field

[0001] This application relates to the field of power grid maintenance technology, and in particular to a power grid operation and maintenance method, apparatus, computer equipment, and computer-readable storage medium. Background Technology

[0002] The power grid is the foundation of a country's energy system, and its safe and efficient operation is directly related to the continuity of power supply and the stability of economic operation.

[0003] In existing technologies, the operation and maintenance of the power grid mainly relies on manual inspections; however, with the continuous increase in the number of equipment in the power generation, transmission and distribution links, and the increasing complexity of the operating environment, manual operation and maintenance methods are becoming increasingly difficult to meet the power grid's demand for operation and maintenance efficiency. Summary of the Invention

[0004] Therefore, it is necessary to provide a power grid operation and maintenance method, device, computer equipment, and computer-readable storage medium that can improve operation and maintenance efficiency in response to the above-mentioned technical problems.

[0005] Firstly, this application provides a power grid operation and maintenance method, the method comprising:

[0006] The system identifies multiple operation and maintenance tasks of the power grid, the relationships between any two operation and maintenance tasks, and a task graph. For any given node, based on the relationships, it determines the conflict edges and dependency edges to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, edges in the task graph represent relationships between different operation and maintenance tasks, the operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other.

[0007] For any conflict edge to which the node belongs, determine the first operation area and first operation time period of the corresponding operation and maintenance task of the node, and the second operation area and second operation time period of the corresponding operation and maintenance task of another node on the conflict edge. Based on the overlapping area between the first operation area and the second operation area, and the overlapping time period between the first operation time period and the second operation time period, obtain the conflict intensity of the node in the task graph.

[0008] Randomly assign any maintenance task to any agent. If the agents corresponding to the two nodes at both ends of any dependency edge are different, determine the importance value of the dependency edge. The importance value represents the importance of the dependency relationship between the two nodes.

[0009] For the corresponding operation and maintenance task and agent, obtain the path length of the shortest travel path between the agent and the operation and maintenance task's work area, and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the agent. Based on the conflict intensity, the importance value, the path length and the matching degree value, adjust the operation and maintenance task assigned to the agent, and control the agent to execute the operation and maintenance task based on the adjustment result.

[0010] Secondly, this application also provides a power grid operation and maintenance device, the device comprising:

[0011] The first determining module is used to determine multiple operation and maintenance tasks of the power grid, the correlation between any two operation and maintenance tasks, and a task graph. For any given node, based on the correlation, it determines the conflict edge and dependency edge to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, edges in the task graph represent the correlation between different operation and maintenance tasks, the operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other.

[0012] The second determining module is used to determine, for any conflict edge to which the node belongs, the first working area and the first working time period of the corresponding operation and maintenance task of the node, and the second working area and the second working time period of the corresponding operation and maintenance task of another node on the conflict edge, and to obtain the conflict intensity of the node in the task graph based on the overlapping area between the first working area and the second working area, and the overlapping time period between the first working time period and the second working time period.

[0013] The allocation module is used to randomly assign any maintenance task to any agent. When the agents corresponding to the two nodes at both ends of any dependency edge are different, the module determines the importance value of the dependency edge. The importance value represents the importance of the dependency relationship between the two nodes.

[0014] The acquisition module is used to acquire, for the corresponding operation and maintenance task and intelligent agent, the path length of the shortest passage between the intelligent agent and the operation and maintenance task's work area, and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the intelligent agent. Based on the conflict intensity, the importance value, the path length and the matching degree value, the operation and maintenance task assigned to the intelligent agent is adjusted, and the intelligent agent is controlled to execute the operation and maintenance task based on the adjustment result.

[0015] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the methods in any of the above embodiments.

[0016] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods in any of the above embodiments.

[0017] The aforementioned power grid operation and maintenance method, apparatus, computer equipment, and computer-readable storage medium determine multiple operation and maintenance tasks of the power grid, the correlation between any two operation and maintenance tasks, and a task graph. For any given node, based on the correlation, the conflict edges and dependency edges to which the node belongs in the task graph are determined. Nodes in the task graph represent operation and maintenance tasks, and edges in the task graph represent the correlation between different operation and maintenance tasks. The operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other. For any conflict edge to which a node belongs, the first operating area and first operating time period of the corresponding operation and maintenance task of the node are determined, as well as the second operating area and second operating time period of the corresponding operation and maintenance task of another node on the conflict edge. Based on the first operating area and the second operating time period... The method identifies the conflict intensity of nodes in the task graph by considering overlapping areas between work areas and overlapping periods between the first and second work periods. It then randomly assigns any maintenance task to any agent, determining the importance value of each dependency edge when the agents corresponding to the two nodes at either end of a dependency edge are different. The importance value represents the degree of importance of the dependency relationship between the two nodes. For each maintenance task and agent, the method obtains the path length of the shortest path between the agent and the work area of ​​the maintenance task, the matching degree between the task type of the maintenance task and the maintenance capability of the agent, and adjusts the maintenance tasks assigned to the agent based on the conflict intensity, importance value, path length, and matching degree. Based on the adjustment result, the method controls the agent to execute the maintenance task. This method not only identifies the agent most suitable for the maintenance task, thus making the execution result of the maintenance task more accurate, but also effectively improves the efficiency of power grid maintenance. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating a power grid operation and maintenance method in one embodiment;

[0020] Figure 2 This is a flowchart illustrating the allocation relationship adjustment steps in one embodiment;

[0021] Figure 3 This is a structural block diagram of a power grid operation and maintenance device in one embodiment;

[0022] Figure 4 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0024] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0025] In one embodiment, such as Figure 1 As shown, a power grid operation and maintenance method is provided. This embodiment illustrates the method applied to a terminal, but it is understood that the method can also be applied to a server, or to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0026] S102. Determine multiple operation and maintenance tasks of the power grid, the relationship between any two operation and maintenance tasks, and the task graph. For any node, based on the relationship, determine the conflict edge and dependency edge to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, and edges in the task graph represent the relationship between different operation and maintenance tasks. The operation and maintenance tasks represented by the nodes at both ends of a conflict edge are in conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other.

[0027] Optionally, the relationships between maintenance tasks may include, but are not limited to, dependency relationships and conflict relationships. For example, if the power equipment corresponding to two maintenance events is connected to the same busbar, and the task types of the maintenance tasks corresponding to these two maintenance events are "busbar maintenance" and "cable replacement" respectively, then according to the procedure, the busbar de-energization operation must be completed before the cable-related work is carried out. Therefore, "cable replacement" depends on "busbar maintenance".

[0028] Optionally, multiple maintenance events in the power grid can be identified first, then a task node set V can be generated through the mapping of events to tasks, and finally, the task node set V can be generated according to the power grid's procedure rule base. Equipment topology diagram Space Usage Table Establish three types of edge relationships between different operation and maintenance tasks: dependency edges Spatial Mutual Exclusion Edge and semantic conflict edge Among them, spatially mutually exclusive edges and semantically conflicting edges are both conflicting edges; for operation and maintenance tasks and ,like Related power equipment and If there is a direct topological connection between related power devices, and their task types belong to a known sequence pair, then construct... and Order-dependent edges between them; if and The locations are mapped to the same physical region, and the time overlap exceeds a threshold. If they are mutually exclusive, then they are considered to be in conflict, and a mutually exclusive edge is established; if and If there is a known conflict between the task types, then a semantic conflict edge is established between them. This edge forms a set... The task graph is formed by the set of nodes V for operation and maintenance tasks. .

[0029] S104. For any conflict edge to which a node belongs, determine the first operating area and first operating time period of the corresponding operation and maintenance task of the node, as well as the second operating area and second operating time period of the corresponding operation and maintenance task of another node on the conflict edge, and obtain the conflict intensity of the node in the task graph based on the overlapping area between the first operating area and the second operating area, and the overlapping time period between the first operating time period and the second operating time period.

[0030] Optionally, maintenance tasks The calculation process for the conflict intensity of the corresponding node is shown in the following formula:

[0031]

[0032] In the formula, Indicates task and Are there conflicting edges between the corresponding nodes? express and The initial conflict intensity between them; This indicates the total number of nodes.

[0033] Optionally, calculations can be performed first based on the overlapping area between the first and second work areas, and the overlapping time period between the first and second work periods. and The degree of spatial overlap and the degree of temporal overlap are considered, and then the product of the spatial overlap and the temporal overlap is determined as the initial conflict intensity. .

[0034] Optionally, after determining the conflict intensity, the embedding vector of any operation and maintenance task can also be determined based on the conflict intensity. The embedding vector must simultaneously reflect the inherent attributes of the operation and maintenance task, its structural position in the task graph, and the logical relationship between the operation and maintenance task and other operation and maintenance tasks; the specific representation of the embedding vector is shown below:

[0035]

[0036] In the formula, The ontology feature vector of the operation and maintenance task is determined based on the urgency level of the corresponding operation and maintenance event, the task type of the operation and maintenance task, and the location information of the associated power equipment. Graph structure density encoding to represent tasks The structural complexity in the task graph is based on the pointers. The number of edges of the corresponding node and The number of edges pointing from the corresponding node to other nodes is calculated using a weighted average.

[0037] S106. Randomly assign any maintenance task to any agent. If the agents corresponding to the two nodes at both ends of any dependency edge are different, determine the importance value of the dependency edge. The importance value represents the importance of the dependency relationship between the two nodes.

[0038] Optionally, the intelligent agent is used to perform operation and maintenance tasks, and the intelligent agent may include, but is not limited to, inspection robots, live-line working arms and drones.

[0039] Optionally, in some embodiments, determining the importance value of the corresponding dependency edge includes: obtaining the level difference between the urgency levels of the corresponding maintenance tasks of the two nodes; and determining the importance value of the corresponding dependency edge based on the level difference. The calculation formula is shown below:

[0040]

[0041] In the formula, and These represent operation and maintenance tasks. and The identifier of the assigned agent; express and The importance value of the dependent edge of the corresponding node is determined by The corresponding level of urgency and It is obtained by adding 1 to the absolute value of the difference between the corresponding urgency levels.

[0042] S108. For the corresponding operation and maintenance task and agent, obtain the path length of the shortest passage between the operation and maintenance task's work area and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the agent. Based on the conflict intensity, importance value, path length and matching degree value, adjust the operation and maintenance task assigned to the agent and control the agent to execute the operation and maintenance task based on the adjustment result.

[0043] Optionally, the conflict intensity, importance value, path length, and matching degree value can be input into a preset function, and the allocation relationship between the agent and the operation and maintenance task can be adjusted multiple times based on the output function result until the output function result meets the preset requirements.

[0044] In the aforementioned power grid operation and maintenance method, multiple operation and maintenance tasks of the power grid, the correlation between any two operation and maintenance tasks, and a task graph are determined. For any given node, based on the correlation, the conflict edges and dependency edges to which the node belongs in the task graph are determined. Nodes in the task graph represent operation and maintenance tasks, and edges in the task graph represent the correlation between different operation and maintenance tasks. The operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, while the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other. For any conflict edge to which a node belongs, the first operating area and first operating time period of the corresponding operation and maintenance task of the node are determined, as well as the second operating area and second operating time period of the corresponding operation and maintenance task of another node on the conflict edge. The overlapping area between the first and second operating areas is then used to determine the first operating area and the second operating time period. The method obtains the conflict intensity of nodes in the task graph, including the domain and the overlapping period between the first and second work periods. It randomly assigns any maintenance task to any agent, and determines the importance value of the dependency edge when the agents corresponding to the two nodes at either end of the dependency edge are different. The importance value represents the importance of the dependency relationship between the two nodes. For the corresponding maintenance task and agent, it obtains the path length of the shortest path between the agent and the work area of ​​the maintenance task, and the matching degree value between the task type of the maintenance task and the maintenance capability of the agent. Based on the conflict intensity, importance value, path length, and matching degree value, the method adjusts the maintenance task assigned to the agent, and controls the agent to execute the maintenance task based on the adjustment result. The method provided in this application can not only determine the agent most suitable for the maintenance task, thus making the execution result of the maintenance task more accurate, but also effectively improve the maintenance efficiency of power grid maintenance.

[0045] In some embodiments, such as Figure 2 As shown, the operational tasks assigned to the agent are adjusted based on conflict intensity, importance value, path length, and matching degree value, including:

[0046] S202. Input the conflict intensity, importance value, path length and matching degree value into the loss function. If the loss function does not converge, adjust the operation and maintenance tasks assigned to the agent.

[0047] S204. Based on the adjusted allocation relationship, return to the step of obtaining the level difference between the urgency levels of the corresponding operation and maintenance tasks of the two nodes, and continue to execute until the loss function converges.

[0048] Alternatively, the loss function is as follows:

[0049]

[0050] In the formula, For the task Work area and intelligent agent The path length of the shortest travel path between them; This indicates the degree of matching between the agent's capabilities and the task type. A capability vector representing an agent. The task type of the operation and maintenance task can be represented by Jaccard or cosine similarity, and the matching degree can be represented by Jaccard or cosine similarity, but is not limited to it. , , , All are cost weights, representing the weight values ​​for path length, matching degree, conflict intensity, and importance, respectively.

[0051] In this embodiment, the quantitative optimization of the allocation of intelligent agent operation and maintenance tasks is realized. By combining multi-dimensional indicators with loss functions, task adjustments are made based on evidence, improving the scientificity and rationality of the allocation. With the convergence of the loss function as the iterative goal, the task allocation scheme is continuously optimized, gradually reducing conflicts and improving the matching degree between intelligent agents and tasks, so that the final allocation result is better.

[0052] In some embodiments, the method further includes: simulating the operation and maintenance process of the power grid by the agent based on the allocation relationship between the operation and maintenance tasks and the agent when the loss function is converged; adjusting the weight values ​​of conflict intensity, importance, path length and matching degree in the loss function to obtain an adjusted loss function if the simulation results are abnormal; returning to the step of randomly assigning any operation and maintenance task to any agent based on the adjusted loss function, and continuing to execute until the simulation results are not abnormal; and determining the target agent to perform the operation and maintenance task based on the allocation relationship between the operation and maintenance tasks and the agent if the simulation results are not abnormal.

[0053] Optionally, the task partitioning process employs a heuristic graph partitioning algorithm. Initially, each agent is directed to its minimum-cost task point set. Through incremental aggregation, local boundary repair, and minimum-cut approximate pruning operations, a stable partitioning state is gradually formed. The execution path of each maintenance task is verified using a simulated scheduler. If there are obvious conflicts, dependency breaks, or resource unreachability in the path, the partitioning is reset and the cost weights are adjusted before partitioning again. For example, in a 220kV substation, there are tasks such as "line overload temperature measurement," "busbar switching preparation," and "switchgear overcurrent action verification." "Busbar switching preparation" depends on the result of "switchgear verification," while "line temperature measurement" is spatially mutually exclusive with other tasks. Assume there are three agents: For operating robots within the station, For live working boom, For inspection drones, temperature measurement tasks will be prioritized and assigned to them. Instead, the other two tasks that have a dependency relationship are grouped together. This ensures that the entire task subgraph is clearly divided in structure and logically coherent.

[0054] In this embodiment, by simulating the operation and maintenance process, the converged task allocation scheme is verified in advance, avoiding abnormal risks in actual execution and ensuring the safety and reliability of power grid operation and maintenance; the operation and maintenance tasks assigned to each agent can simultaneously meet the requirements of conflict reduction, dependency maintenance and resource matching.

[0055] In some embodiments, controlling the agent to execute maintenance tasks based on the adjustment results includes: sorting all maintenance tasks corresponding to the same target agent in order of execution from front to back; for the target agent, during the process of the target agent executing maintenance tasks sequentially according to the sorting results, determining the first maintenance task in the sorting results among all unexecuted maintenance tasks; if the execution conditions of the first maintenance task are not met, determining the urgency level of any remaining maintenance task after the first maintenance task, and the number of edges between the node corresponding to the first maintenance task and the node corresponding to the remaining maintenance tasks; based on the urgency level and number of remaining maintenance tasks, selecting one maintenance task from all remaining maintenance tasks, and using the selected maintenance task as the new first maintenance task in the sorting results.

[0056] Optionally, the generation of the ordering results for maintenance tasks needs to consider not only the dependency order between tasks, but also the current system status and power operation safety procedures. For example, in a substation operation scenario, the task "power off switchgear" must precede "open switchgear door," and "open door" is a prerequisite task for "equipment replacement." This kind of order is not only reflected in the directed edges of the task graph, but also in the strict requirements on the operation window, electrical status, and environmental conditions during actual execution. Therefore, before task ordering, the system needs to perform "state feasibility screening" on the task graph to remove task nodes that are temporarily unable to be executed.

[0057] Optionally, if the task The execution of a task requires the device to be in a "cold standby" state. However, if the current real-time SCADA status does not meet this condition, the task will be temporarily placed in the candidate list and will not participate in the first round of sorting.

[0058] Optionally, if the task If it is not executable under the current conditions, then it is ranked in the sorting results as a task. In subsequent maintenance tasks, select the task with the fewest structural conflicts and the highest urgency level to replace the task. The specific selection formula is shown below:

[0059]

[0060] In the formula, Selected for replacement The identifier for the operation and maintenance task; Indicates the position in the sorting results The collection of all subsequent tasks; express To the mission The path depth, i.e. and The number of edges between them; express The level of urgency; Prioritize the penalty weight for skipping.

[0061] Optionally, for example, before executing a "remote closing of disconnector" task, if the system detects a "closing condition not met" status, then the task... Suspended, and from Find the most suitable one in the subsequent tasks Prioritize tasks with higher priority and shorter paths to avoid system idleness and resource waiting.

[0062] In this embodiment, the agent is allowed to dynamically select an alternative task when the conditions for the execution of the first task are not met, so as to avoid execution stagnation and improve the continuity of operation and maintenance. The selection is combined with the urgency level and the number of edges between nodes, taking into account the task priority and dependency relationship, so as to ensure that the scheduling is reasonable and compliant.

[0063] In some embodiments, after sorting all maintenance tasks corresponding to the same target agent in order of execution from front to back, the method further includes: for any maintenance task, obtaining a sorting evaluation value for the maintenance task based on the urgency level of the maintenance task, the path length of the shortest path between the target agent and the operation area of ​​the maintenance task, and the order of the maintenance task with other maintenance tasks in the sorting result; if the sorting evaluation value is less than the evaluation value threshold, re-determining the execution order of the maintenance tasks.

[0064] Optionally, the calculation process for the ranking evaluation value is shown in the following formula:

[0065]

[0066] In the formula, According to the level of urgency, This represents the path length of the shortest travel path between the target intelligent agent and the operation and maintenance task's work area. Indicates task The set of all tasks it depends on; A Boolean function, representing Has the result already been sorted? Previously, if not, this item would be 0.

[0067] In this embodiment, the ranking evaluation value is calculated by combining multiple dimensions such as urgency, path length and task order, so as to realize the quantitative evaluation of the ranking of operation and maintenance tasks and improve the scientificity and rationality of the ranking. The execution order of tasks with ranking evaluation values ​​below the threshold is readjusted to optimize the execution timing and take into account both task priority and agent operation efficiency.

[0068] In some embodiments, determining multiple operation and maintenance tasks of the power grid and the correlation between any two operation and maintenance tasks includes: real-time monitoring of multi-source operation data of the power grid; if the change in the value of at least one type of operation data within the current monitoring period is greater than the corresponding data value threshold, determining the maintenance events to be performed within the current monitoring period based on preset event filtering rules; obtaining the event type, occurrence timestamp, and urgency level of the maintenance events, as well as the equipment identifier and location information of the power equipment associated with the maintenance events; and for any two maintenance events occurring within multiple monitoring periods, determining the corresponding operation and maintenance task for any one maintenance event and the correlation between any two operation and maintenance tasks based on the event type, occurrence timestamp, urgency level, equipment identifier, and location information.

[0069] Optionally, multi-source operational data may include, but is not limited to, power grid operational status data, binary signals, and operation and maintenance dispatching task plan data. Operational status data may include, but is not limited to, three-phase current, voltage, frequency, active power, and reactive power. This data can be collected at a second-level sampling frequency by the SCADA (Supervisory Control And Data Acquisition) system at the station control layer and stored in a real-time database. Each data point has a distinct device ID, acquisition timestamp, and data channel number. Binary signals may include, but are not limited to, trip signals, protection start signals, and switch status change signals. These signals may originate from relay protection equipment and switch status remote signaling. Each status change triggers a remote signaling refresh, and they are typically uploaded to the dispatching system via the IEC-60870 or IEC-61850 protocol. Operation and maintenance dispatching task plan data comes from the task management module in the dispatching platform and is usually stored in structured record form. Each record may include, but is not limited to, the dispatching task number, target equipment, expected start time, duration, and responsible unit.

[0070] Optionally, if the value of a certain operational data exceeds a corresponding data value threshold within a certain monitoring period, a maintenance event can be determined based on that operational data; the judgment logic is as follows:

[0071]

[0072] In the formula, This represents the event trigger identifier for the maintenance event pending for the i-th power device at time t; This represents the data value of the i-th power device at time t. Indicates the monitoring period; the form can be set to 30 seconds or more. This represents the threshold value corresponding to the operating data of the i-th power device; This is an indicator function; a value of 1 indicates that the event has been triggered, and a value of 0 indicates that it has not been triggered.

[0073] Optionally, the preset event filtering rules can be set based on the power grid regulations; for example, for transmission lines, a three-phase imbalance exceeding 10% and lasting for more than 10 seconds must be identified as a "line abnormality" event to be maintained; for transformers, only when the winding temperature exceeds the alarm threshold and is accompanied by a load rate exceeding 95% is it identified as a "heavy load event"; if a scheduling plan task overlaps with a sudden change in equipment time, it is regarded as an "unplanned operation conflict event".

[0074] Optionally, after filtering the events to be maintained, a structured tuple can be constructed for each remaining event. All elements in this structured tuple collectively determine whether a corresponding maintenance task can be constructed for that event. The structured tuple is shown in the following formula:

[0075]

[0076] In the formula, The device identifier for the power equipment associated with the maintenance event. For the location information of power equipment, The event type for events awaiting maintenance. This is the timestamp of the event to be maintained. This indicates the urgency level of the maintenance event. The higher the level, the more urgent the event is and the more priority it needs to be addressed.

[0077] Optionally, in one embodiment, when 110kV line #3 trips, the remote signaling channel number LN3_TRIP changes from 0 to 1. Simultaneously, 110kV line #2 experiences a short-term overcurrent, with the current abruptly changing from 420A to 765A. The maintenance events at this time constitute a set of "line concurrent anomalies," which are mapped to two event tuples. and ,in, The type is "protective action". The type is "overload event", and the two share spatial location information and are highly correlated in time.

[0078] Optionally, the resulting set of events to be maintained can ultimately be expressed as a set. , of which each All of them have clear equipment orientation, time positioning and type structure, and all events have been verified by procedures and rules, with clear engineering semantics and practical operation orientation.

[0079] In this embodiment, by monitoring multi-source operation data in real time and combining it with the quantitative judgment standard of "change exceeding the threshold", we can avoid missing the judgment of power grid anomalies. Then, through preset rule filtering, invalid fluctuations are eliminated to ensure that the maintenance events focus on real maintenance needs and reduce invalid responses.

[0080] In one exemplary embodiment, another power grid operation and maintenance method is provided, which includes the following:

[0081] (1) By collecting key operating indicators of continuous operation in the power production environment, within a time window If any key operational indicator changes beyond a set threshold, it is considered a candidate event. Then, valid events are further filtered through rule filtering and event structuring mechanisms, and a set of events is obtained by summarizing them.

[0082] (2) A task node set is generated by mapping events to tasks. Three types of edge relationships between tasks are established based on the procedure rule base, device topology diagram and space occupancy table, including sequential dependency edge, spatial mutual exclusion edge and semantic conflict edge. The edge set is then combined with the task node set to form a complete task graph. Each task node in the task graph is constructed with an embedded representation based on a structure-aware static embedding method.

[0083] (3) Based on the heterogeneous capabilities of agents in the power production environment, resource allocation tasks are divided using a heuristic graph partitioning algorithm. Each agent is directed to the task point set with the minimum cost, and the task subgraph partitioning result corresponding to each agent is obtained.

[0084] (4) A ranking score is assigned to each task node by adopting a structural priority fusion ranking mechanism. After ranking the scores from high to low, the ranking sequence is sent to the device of the relevant agent for path planning. When the task fails, a replacement task node is found through a local replacement mechanism.

[0085] It should be understood that although the steps in the flowcharts of the embodiments described above 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 flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0086] Based on the same inventive concept, this application also provides a power grid operation and maintenance device for implementing the power grid operation and maintenance method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more power grid operation and maintenance device embodiments provided below can be found in the limitations of the power grid operation and maintenance method described above, and will not be repeated here.

[0087] In one exemplary embodiment, such as Figure 3 As shown, a power grid operation and maintenance device 300 is provided, including: a first determining module 301, a second determining module 302, an allocation module 303, and an acquisition module 304, wherein:

[0088] The first determining module 301 is used to determine multiple operation and maintenance tasks of the power grid, the association between any two operation and maintenance tasks, and a task graph. For any given node, based on the association, it determines the conflict edge and dependency edge to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, edges in the task graph represent the association between different operation and maintenance tasks, the operation and maintenance tasks represented by the nodes at both ends of the conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of the dependency edge have a dependency relationship.

[0089] The second determining module 302 is used to determine, for any conflict edge to which the node belongs, the first operating area and the first operating time period of the corresponding operation and maintenance task of the node, and the second operating area and the second operating time period of the corresponding operation and maintenance task of another node on the conflict edge, and to obtain the conflict intensity of the node in the task graph based on the overlapping area between the first operating area and the second operating area, and the overlapping time period between the first operating time period and the second operating time period.

[0090] The allocation module 303 is used to randomly assign any maintenance task to any agent, and determine the importance value of the dependency edge when the agents corresponding to the two nodes at both ends of any dependency edge are different; wherein, the importance value represents the importance of the dependency relationship between the two nodes.

[0091] The acquisition module 304 is used to acquire, for the corresponding operation and maintenance task and intelligent agent, the path length of the shortest passage between the intelligent agent and the operation and maintenance task's work area, and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the intelligent agent. Based on the conflict intensity, the importance value, the path length and the matching degree value, the operation and maintenance task assigned to the intelligent agent is adjusted, and the intelligent agent is controlled to execute the operation and maintenance task based on the adjustment result.

[0092] In some embodiments, the allocation module 303 is further configured to obtain the level difference between the urgency levels of the corresponding maintenance tasks of the two nodes; and determine the importance value of the corresponding dependent edge based on the level difference.

[0093] In some embodiments, the acquisition module 304 is further configured to input the conflict intensity, the importance value, the path length and the matching degree value into the loss function, and adjust the operation and maintenance tasks assigned to the agent if the loss function does not converge; based on the adjusted allocation relationship, return to the step of obtaining the level difference between the urgency levels of the corresponding operation and maintenance tasks of the two nodes, and continue to execute until the loss function converges.

[0094] In some embodiments, the acquisition module 304 is further configured to: simulate the operation and maintenance process of the power grid by the intelligent agent based on the allocation relationship between the operation and maintenance task and the intelligent agent when the loss function is converged; adjust the weight values ​​of the conflict intensity, importance, path length and matching degree in the loss function if the simulation result is abnormal, to obtain an adjusted loss function; return to the step of randomly assigning any operation and maintenance task to any intelligent agent based on the adjusted loss function, and continue execution until the simulation result is not abnormal; and determine the target intelligent agent to execute the operation and maintenance task based on the allocation relationship between the operation and maintenance task and the intelligent agent if the simulation result is not abnormal.

[0095] In some embodiments, the acquisition module 304 is further configured to sort all maintenance tasks corresponding to the same target agent according to the execution order from front to back; for the target agent, during the process of the target agent executing maintenance tasks sequentially according to the sorting result, determine the first maintenance task in the sorting result among all unexecuted maintenance tasks; if the execution conditions of the first maintenance task are not met, determine the urgency level of any remaining maintenance task after the first maintenance task, and the number of edges between the node corresponding to the first maintenance task and the node corresponding to the remaining maintenance task; based on the urgency level and the number of remaining maintenance tasks, select one maintenance task from all remaining maintenance tasks, and use the selected maintenance task as the new first maintenance task in the sorting result.

[0096] In some embodiments, the acquisition module 304 is further configured to, for any one operation and maintenance task, acquire a corresponding ranking evaluation value for the operation and maintenance task based on the urgency level of the operation and maintenance task, the path length of the shortest travel path between the target agent and the operation and maintenance task's work area, and the order of the operation and maintenance task with other operation and maintenance tasks in the ranking result; and, if the ranking evaluation value is less than the evaluation value threshold, redetermine the execution order of the operation and maintenance task.

[0097] In some embodiments, the first determining module 301 is further configured to monitor the multi-source operation data of the power grid in real time, and, if the change in the data value of at least one type of operation data within the current monitoring period is greater than the corresponding data value threshold of the operation data, determine the maintenance events that occurred within the current monitoring period based on preset event filtering rules; obtain the event type, occurrence timestamp, and urgency level of the maintenance events, as well as the device identifier and location information of the power equipment associated with the maintenance events; and, for any two maintenance events occurring within multiple monitoring periods, determine the maintenance tasks corresponding to any one maintenance event and the association between any two maintenance tasks based on the event type, the occurrence timestamp, the urgency level, the device identifier, and the location information.

[0098] Each module in the aforementioned power grid operation and maintenance device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0099] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a power grid operation and maintenance method.

[0100] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0102] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0103] 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, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0104] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0105] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0106] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A power grid operation and maintenance method, characterized in that, The method includes: The system identifies multiple operation and maintenance tasks of the power grid, the relationships between any two operation and maintenance tasks, and a task graph. For any given node, based on the relationships, it determines the conflict edges and dependency edges to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, edges in the task graph represent relationships between different operation and maintenance tasks, the operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other. For any conflict edge to which the node belongs, determine the first operation area and first operation time period of the corresponding operation and maintenance task of the node, and the second operation area and second operation time period of the corresponding operation and maintenance task of another node on the conflict edge. Based on the overlapping area between the first operation area and the second operation area, and the overlapping time period between the first operation time period and the second operation time period, obtain the conflict intensity of the node in the task graph. Randomly assign any maintenance task to any agent. If the agents corresponding to the two nodes at both ends of any dependency edge are different, determine the importance value of the dependency edge. The importance value represents the importance of the dependency relationship between the two nodes. For the corresponding operation and maintenance task and intelligent agent, obtain the path length of the shortest passage between the intelligent agent and the operation and maintenance task's work area, and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the intelligent agent. Based on the conflict intensity, the importance value, the path length and the matching degree value, adjust the operation and maintenance task assigned to the intelligent agent, and control the intelligent agent to execute the operation and maintenance task based on the adjustment result. The step of adjusting the maintenance tasks assigned to the agent based on the conflict intensity, importance value, path length, and matching degree value includes: inputting the conflict intensity, importance value, path length, and matching degree value into a loss function; adjusting the maintenance tasks assigned to the agent if the loss function does not converge; and, based on the adjusted assignment relationship, returning to the step of obtaining the level difference between the urgency levels of the corresponding maintenance tasks of the two nodes, and continuing execution until the loss function converges. The method further includes: simulating the operation and maintenance process of the power grid by the agent based on the allocation relationship between the operation and maintenance task and the agent when the loss function is converged; adjusting the weight values ​​of the conflict intensity, importance, path length, and matching degree in the loss function to obtain an adjusted loss function if the simulation results are abnormal; returning to the step of randomly assigning any operation and maintenance task to any agent based on the adjusted loss function, and continuing execution until the simulation results are normal; and determining the target agent to execute the operation and maintenance task based on the allocation relationship between the operation and maintenance task and the agent if the simulation results are normal.

2. The method according to claim 1, characterized in that, Determining the importance value of the corresponding dependency edge includes: Obtain the urgency level difference between the corresponding maintenance tasks of the two nodes; The importance value of the dependent edge is determined based on the level difference.

3. The method according to claim 1, characterized in that, The process of controlling the intelligent agent to execute the operation and maintenance task based on the adjustment result includes: All maintenance tasks corresponding to the same target intelligent agent are sorted in the order of execution from front to back; For the target intelligent agent, during the process of the target intelligent agent executing operation and maintenance tasks in sequence according to the sorting result, the first operation and maintenance task in the sorting result among all unexecuted operation and maintenance tasks is determined; If the execution conditions of the first maintenance task are not met, determine the urgency level of any remaining maintenance task after the first maintenance task, and the number of edges between the corresponding node of the first maintenance task and the corresponding node of the remaining maintenance task. Based on the urgency level and quantity of the remaining maintenance tasks, one maintenance task is selected from all remaining maintenance tasks, and the selected maintenance task is used as the new first maintenance task in the sorting result.

4. The method according to claim 3, characterized in that, After sorting all maintenance tasks corresponding to the same target intelligent agent in order of execution from front to back, it also includes: For any maintenance task, based on the urgency level of the maintenance task, the path length of the shortest travel path between the target agent and the operation area of ​​the maintenance task, and the order of the maintenance task with other maintenance tasks in the ranking results, the corresponding ranking evaluation value of the maintenance task is obtained. If the sorting evaluation value is less than the evaluation value threshold, the execution order of the operation and maintenance tasks will be re-determined.

5. The method according to claim 1, characterized in that, The determination of the relationships between multiple operation and maintenance tasks of the power grid and between any two operation and maintenance tasks includes: Real-time monitoring of multi-source operation data of the power grid; if the change in the value of at least one type of operation data within the current monitoring period is greater than the corresponding data value threshold of the operation data, the maintenance events that occur within the current monitoring period are determined based on preset event filtering rules. Obtain the event type, occurrence timestamp, and urgency level of the event to be maintained, as well as the device identifier and location information of the power equipment associated with the event to be maintained; For any two maintenance events occurring within multiple monitoring periods, based on the event type, the occurrence timestamp, the urgency level, the device identifier, and the location information, determine the maintenance task corresponding to any one maintenance event and the association between any two maintenance tasks.

6. A power grid operation and maintenance device, characterized in that, The device includes: The first determining module is used to determine multiple operation and maintenance tasks of the power grid, the correlation between any two operation and maintenance tasks, and a task graph. For any given node, based on the correlation, it determines the conflict edge and dependency edge to which the node belongs in the task graph. Nodes in the task graph represent operation and maintenance tasks, edges in the task graph represent the correlation between different operation and maintenance tasks, the operation and maintenance tasks represented by the nodes at both ends of a conflict edge conflict with each other, and the operation and maintenance tasks represented by the nodes at both ends of a dependency edge are dependent on each other. The second determining module is used to determine, for any conflict edge to which the node belongs, the first working area and the first working time period of the corresponding operation and maintenance task of the node, and the second working area and the second working time period of the corresponding operation and maintenance task of another node on the conflict edge, and to obtain the conflict intensity of the node in the task graph based on the overlapping area between the first working area and the second working area, and the overlapping time period between the first working time period and the second working time period. The allocation module is used to randomly assign any maintenance task to any agent. When the agents corresponding to the two nodes at both ends of any dependency edge are different, the module determines the importance value of the dependency edge. The importance value represents the importance of the dependency relationship between the two nodes. The acquisition module is used to acquire, for the corresponding operation and maintenance task and intelligent agent, the path length of the shortest passage between the operation and maintenance task's work area and the matching degree value between the task type of the operation and maintenance task and the operation and maintenance capability of the intelligent agent, adjust the operation and maintenance task assigned to the intelligent agent based on the conflict intensity, the importance value, the path length and the matching degree value, and control the intelligent agent to execute the operation and maintenance task based on the adjustment result; The acquisition module is further configured to input the conflict intensity, the importance value, the path length, and the matching degree value into the loss function; if the loss function does not converge, adjust the operation and maintenance tasks assigned to the agent; based on the adjusted allocation relationship, return to the step of obtaining the level difference between the urgency levels of the corresponding operation and maintenance tasks of the two nodes, and continue execution until the loss function converges. The acquisition module is further configured to simulate the operation and maintenance process of the power grid by the intelligent agent based on the allocation relationship between the operation and maintenance task and the intelligent agent when the loss function is converged; if there are abnormalities in the simulation results, adjust the weight values ​​of the conflict intensity, importance, path length and matching degree in the loss function to obtain an adjusted loss function; based on the adjusted loss function, return to the step of randomly assigning any operation and maintenance task to any intelligent agent, and continue execution until there are no abnormalities in the simulation results; if there are no abnormalities in the simulation results, determine the target intelligent agent to execute the operation and maintenance task based on the allocation relationship between the operation and maintenance task and the intelligent agent.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images