Multi-agent cooperative power equipment management method and device, equipment and medium

Abstract

The application relates to a power equipment management method and device based on multi-agent cooperation, equipment and medium. The method comprises the following steps: for each typhoon prediction path, a second agent is used to determine the power equipment affected by the typhoon prediction path from a plurality of power equipment according to the device attribute information of the plurality of power equipment, and a power equipment set corresponding to the typhoon prediction path is obtained; for each power equipment set, a second agent is used to perform risk assessment on the power equipment set according to the device operation data of the power equipment in the power equipment set and the typhoon prediction path corresponding to the power equipment set, and a risk warning value of the power equipment set is determined; a fourth agent is used to screen a target power equipment set from the plurality of power equipment sets according to the risk warning value, and the management of the power equipment is performed according to the target power equipment set. The method can improve the risk prediction accuracy of the power equipment.

Description

Technical Field

[0001] This application relates to the field of power equipment management technology, and in particular to a method, apparatus, equipment and medium for multi-agent collaborative power equipment management. Background Technology

[0002] With the expansion of the power system and the frequent occurrence of extreme weather events such as typhoons, power grid companies have increasingly stringent requirements for the intelligent management of power equipment and the efficiency of disaster emergency response. In typhoon scenarios, it is necessary to accurately predict the equipment affected, efficiently collect equipment data, and quickly dispatch operation and maintenance resources to reduce the damage of disasters to the power supply network.

[0003] Traditional technologies mainly rely on manual inspections and static monitoring, using fixed sensors to collect local data and combining it with the basic attributes of the equipment for risk assessment.

[0004] However, traditional methods suffer from low accuracy in predicting risks to power equipment. Summary of the Invention

[0005] Therefore, it is necessary to provide a multi-agent collaborative power equipment management method, device, equipment, and medium that can improve the accuracy of power equipment risk prediction, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a multi-agent collaborative power equipment management method, including:

[0007] Typhoon meteorological data is obtained through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon.

[0008] For each typhoon forecast path, the second intelligent agent determines the power equipment affected on the typhoon forecast path based on the equipment attribute information of multiple power equipment, and obtains the set of power equipment corresponding to the typhoon forecast path.

[0009] For each set of power devices, a third-party intelligent agent is used to obtain the device operation data of each power device in the set of power devices;

[0010] For each set of power equipment, a second intelligent agent performs a risk assessment based on the equipment operation data of the power equipment in the set and the typhoon forecast path corresponding to the set of power equipment, and determines the risk warning value of the set of power equipment.

[0011] The fourth intelligent agent filters out the target set of power equipment from multiple sets of power equipment based on the risk warning value, and generates an equipment management report based on the target set of power equipment. The equipment management report is used for the management of power equipment.

[0012] Secondly, this application also provides a multi-agent collaborative power equipment management device, comprising:

[0013] The acquisition module is used to acquire typhoon meteorological data through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon.

[0014] The matching module is used to determine the power equipment affected on the typhoon prediction path for each typhoon prediction path through a second intelligent agent based on the equipment attribute information of multiple power equipment, and obtain the set of power equipment corresponding to the typhoon prediction path.

[0015] The acquisition module is also used to obtain the equipment operation data of each power device in the power device set using a third intelligent agent for each power device set;

[0016] The prediction module is used to conduct risk assessment for each power equipment set through a second intelligent agent, based on the equipment operation data of the power equipment in the power equipment set and the typhoon prediction path corresponding to the power equipment set, and determine the risk warning value of the power equipment set.

[0017] The generation module is used by a fourth intelligent agent to filter out a target set of power equipment from multiple sets of power equipment based on risk warning values, and generate an equipment management report based on the target set of power equipment. The equipment management report is used for the management of power equipment.

[0018] Thirdly, this application also provides a computer device, 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-described multi-agent cooperative power equipment management method.

[0019] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above-described multi-agent cooperative power equipment management method.

[0020] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps in the above-described multi-agent collaborative power equipment management method.

[0021] The aforementioned multi-agent collaborative power equipment management methods, devices, equipment, and media, through the fusion processing of multi-source typhoon prediction paths by the first agent in the multi-agent collaborative architecture, help alleviate the limitations of traditional meteorological data collection, which has relatively limited coverage. Relying on the real-time acquisition capabilities of the third agent, it can improve the problem of lag in equipment operation data collection under extreme weather conditions to a certain extent. The comprehensive assessment conducted by the second agent, combining spatial matching mechanisms and dynamic operation data, improves the accuracy of identifying affected power equipment and optimizes the refinement of risk assessment, thereby alleviating the shortcomings of relatively rough and static risk assessment in traditional models. The fourth agent, through multi-dimensional priority ranking and adaptive report generation, can promote closed-loop management from risk warning to disposal, improving the efficiency of emergency response. The overall multi-agent architecture, with its parallel processing, professional adaptation, and distributed fault tolerance characteristics, improves the reliability of the power supply system and the level of intelligence in emergency management under extreme weather conditions. Attached Figure Description

[0022] 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.

[0023] Figure 1 This is an application environment diagram of a multi-agent collaborative power equipment management method in one embodiment;

[0024] Figure 2 This is a flowchart illustrating a multi-agent collaborative power equipment management method in one embodiment;

[0025] Figure 3 This is a flowchart illustrating a multi-agent collaborative power equipment management method in another embodiment;

[0026] Figure 4 This is a structural block diagram of a multi-agent collaborative power equipment management device in one embodiment;

[0027] Figure 5 This is an internal structural diagram of a computer device in one embodiment;

[0028] Figure 6 This is an internal structural diagram of a computer device in yet another embodiment. Detailed Implementation

[0029] 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.

[0030] 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.

[0031] The multi-agent collaborative power equipment management method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. Terminal 102 sends a power equipment management request to server 104. Server 104 responds to the power equipment management request and obtains typhoon meteorological data through a first intelligent agent. The typhoon meteorological data includes multiple typhoon forecast paths corresponding to the typhoon. For each typhoon forecast path, a second intelligent agent determines the power equipment affected on the typhoon forecast path based on the equipment attribute information of multiple power equipment, thus obtaining a set of power equipment corresponding to the typhoon forecast path. For each set of power equipment, a third intelligent agent obtains the equipment operation data of each power equipment in the set. For each set of power equipment, the second intelligent agent performs a risk assessment based on the equipment operation data of the power equipment in the set and the typhoon forecast path corresponding to the set, determining the risk warning value of the set of power equipment. A fourth intelligent agent filters out the target set of power equipment from multiple sets of power equipment based on the risk warning value and generates an equipment management report based on the target set of power equipment. The equipment management report is used for the management of power equipment, and server 104 returns the equipment management report to terminal 102. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0032] In one exemplary embodiment, such as Figure 2 As shown, a multi-agent collaborative power equipment management method is provided, which can be applied to... Figure 1 Taking the server in the example of this, the explanation includes:

[0033] Step 201: Obtain typhoon meteorological data through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon.

[0034] It is worth noting that this embodiment deploys four types of intelligent agents, including a meteorological intelligent agent, an affected equipment prediction intelligent agent, a damaged equipment information acquisition intelligent agent, and an equipment damage information aggregation and analysis intelligent agent. At the same time, a central coordinator is established to manage the instruction recognition, task allocation, and data exchange among the four types of intelligent agents. Furthermore, the four types of intelligent agents communicate asynchronously through a shared data bus, message queue, or API interface. After converting the data to be transmitted into binary code, the intelligent agents complete the data transmission between each other through wired or wireless transmission methods.

[0035] Among them, the first intelligent agent can be a meteorological intelligent agent, which serves as the entry point for collecting typhoon-related data and is responsible for acquiring typhoon meteorological data. Typhoon meteorological data includes, but is not limited to, the current development stage of the typhoon, the real-time path information of the typhoon, the expected future movement path, the expected intensity, the real-time location of the typhoon center and the radius of the wind circle, etc. The predicted path of the typhoon can be the expected future movement path.

[0036] Optionally, external inputs can be monitored in real time through a central coordinator. When a typhoon warning instruction is received or a meteorological agent detects a typhoon event, the central coordinator broadcasts an activation instruction to the agent, triggering a collaborative task process. Each agent identifies the relevant instructions according to its preset responsibilities. Among them, the central coordinator sends a meteorological data collection instruction to the meteorological agent, which identifies the meteorological data collection instruction and continuously monitors the typhoon's development stage, real-time path, and expected movement path data.

[0037] Step 202: For each typhoon forecast path, the second intelligent agent determines the power equipment affected on the typhoon forecast path from among the multiple power equipment based on the equipment attribute information of each power equipment, and obtains the set of power equipment corresponding to the typhoon forecast path.

[0038] The second intelligent agent can be an intelligent agent that predicts the affected equipment; the equipment attribute information can be key parameters inherent to the power equipment itself, used to assess its typhoon resistance capability, including but not limited to the equipment's wind resistance level, waterproof level, installation area, equipment type, and equipment commissioning years; the power equipment set can be a set of all power equipment affected by typhoons along a single typhoon prediction path, determined by the second intelligent agent through screening, and all power equipment in the set are target equipment that are at risk of damage under the typhoon prediction path.

[0039] Optionally, the central coordinator drives the meteorological agent to collect typhoon meteorological data and pushes it to the affected equipment prediction agent; the central coordinator assigns prediction tasks to the affected equipment prediction agent, and the affected equipment prediction agent recognizes the equipment prediction instructions. When it receives meteorological data or central instructions, it starts the affected equipment prediction process; the affected equipment prediction agent takes the typhoon meteorological data as input, performs spatial matching and capability adaptation two-dimensional correlation analysis through the typhoon prediction path in the typhoon meteorological data, and combines the equipment attribute information of the power equipment itself to predict the power equipment affected by the typhoon, thereby obtaining the set of power equipment corresponding to the typhoon prediction path.

[0040] In one embodiment, the equipment attribute information includes installation location information and equipment attribute features. Based on the equipment attribute information of each of the multiple power devices, the power devices affected by the typhoon forecast path are determined from the multiple power devices, including: determining the power devices covered by the typhoon on the typhoon forecast path from the multiple power devices based on the installation location information of each of the multiple power devices; and filtering the power devices affected by the typhoon forecast path from the power devices covered by the typhoon based on the equipment attribute features, where the equipment attribute features are used to reflect the risk resistance capability of the power devices.

[0041] The installation location information can be the actual installation location of the power equipment, and the equipment attribute characteristics include, but are not limited to, wind resistance level, waterproof level, installation area, equipment type, and equipment commissioning years.

[0042] Optionally, the affected equipment prediction agent uses typhoon meteorological data as input and performs spatial matching and capability adaptation correlation analysis to predict the power equipment affected by the typhoon and its location, combined with the power equipment's own attributes. These attributes include wind resistance level, waterproof level, installation area, equipment type, and equipment commissioning year. Based on the typhoon prediction path, spatial matching is performed with the installation location of the power equipment to initially identify equipment areas potentially covered by the typhoon. Then, combined with the expected typhoon intensity in this area, capability adaptation is performed with the power equipment's own attribute characteristics to screen out the power equipment affected by the typhoon and its corresponding areas. Simultaneously, combining the characteristics of high-risk power equipment under preset typhoon and flood prevention scenarios, these characteristics are identified and matched with the power equipment's own attribute characteristics. Equipment matching these characteristics is classified as high-risk power equipment, thus screening out the power equipment affected along the typhoon prediction path.

[0043] Step 203: For each set of power devices, use a third-party intelligent agent to obtain the device operation data of each power device in the set of power devices.

[0044] Among them, the third intelligent agent can be an intelligent agent for acquiring information about damaged equipment, and the equipment operation data can be historical operating status data and video data of the power equipment. The video data includes videos reflecting the status of the power equipment itself and videos of the surrounding environment of the unpredicted damaged power equipment.

[0045] Optionally, the intelligent agent for acquiring damaged equipment information is used to trigger data collection tasks based on equipment priority and suddenly damaged equipment, and then collect the equipment operation data of the power equipment in each power equipment set according to equipment priority; if there is suddenly damaged equipment, the equipment operation data of the suddenly damaged equipment can be collected simultaneously. It is worth noting that suddenly damaged equipment can be power equipment that actually malfunctions or is abnormal during a typhoon event but is not included in the power equipment set.

[0046] In one embodiment, obtaining the equipment operation data of each power device in the power equipment set using a third intelligent agent further includes: using a second intelligent agent to determine the typhoon event characteristics of the current typhoon at the location corresponding to each power device in the power equipment set based on typhoon meteorological data, and determining at least one historical typhoon associated with each power device based on the typhoon event characteristics; using the second intelligent agent to determine the equipment priority of each power device in the power equipment set based on the fault records of each power device under historical typhoons; and using the third intelligent agent to collect the equipment operation data of each power device in the power equipment set according to the equipment priority of the power devices in the power equipment set.

[0047] Among them, equipment priority can be a risk level ranking index of power equipment in typhoon scenarios, which is generated quantitatively based on rules such as the historical vulnerability of equipment and its current health status, and is used to guide the order of data collection.

[0048] Optionally, based on the identified high-risk power equipment, historical fault association and current health status verification are introduced. Power equipment that meets either the conditions of historically vulnerable equipment and / or currently sub-healthy equipment is identified as potentially damaged power equipment. The historical fault association is defined as follows: fault records under similar typhoon scenarios are retrieved from the equipment operation and maintenance ledger system. If the power equipment has previously experienced a fault under the same wind force and rainfall conditions, it is marked as historically vulnerable equipment. The current health status verification is defined as follows: combining real-time equipment monitoring data, if the power equipment currently has unrepaired defects, it is marked as currently sub-healthy equipment. The priority of predicted damaged equipment is output, and the specific sorting rule follows: power equipment that meets both the conditions of historically vulnerable equipment and currently sub-healthy equipment has the highest priority, followed by power equipment that meets the conditions of historically vulnerable equipment, and then power equipment that meets the conditions of currently sub-healthy equipment. Then, according to the equipment priority of the power equipment in the power equipment set, the equipment operation data of each power equipment in the power equipment set is collected. It is worth noting that if there is suddenly damaged equipment, the equipment operation data of the suddenly damaged equipment can be collected simultaneously.

[0049] Step 204: For each power equipment set, the second intelligent agent performs a risk assessment based on the equipment operation data of the power equipment in the power equipment set and the typhoon forecast path corresponding to the power equipment set, and determines the risk warning value of the power equipment set.

[0050] Among them, the risk warning value can be a quantitative indicator output by the risk assessment model, which is used to characterize the overall risk level of a specific set of power equipment under the corresponding typhoon prediction path, and its value directly reflects the warning priority of the set.

[0051] Optionally, under the command and dispatch of the central coordinator, the affected equipment prediction agent calculates the expected failure risk intensity of the equipment based on the equipment operation data and the typhoon prediction path corresponding to the power equipment set, and then combines the risk matching value and the early warning model formula to complete the quantitative determination of the risk early warning value of the power equipment set, that is, to obtain the risk early warning value of the power equipment set.

[0052] Step 205: The fourth intelligent agent filters out the target power equipment set from multiple power equipment sets based on the risk warning value, and generates an equipment management report based on the target power equipment set. The equipment management report is used for the management of power equipment.

[0053] The target power equipment set can be a high-risk subset selected from multiple sets based on risk warning values; the equipment management report can be a professional operation and maintenance guidance document compiled by the fourth intelligent agent based on the risk data of the target power equipment set, including core contents such as an abnormal risk equipment list, equipment risk frequency statistics, priority reinforcement equipment ranking, and risk retest results after reinforcement.

[0054] Optionally, the fourth intelligent agent, as the intelligent agent for aggregating and analyzing equipment damage information, under the command and scheduling of the central coordinator, first selects the target set of power equipment with excessive risk from multiple sets of power equipment based on preset thresholds, then determines the priority equipment to be reinforced by statistically analyzing the frequency of equipment risks and conducts iterative risk retesting, and finally integrates all the data to form an equipment management report and pushes it to the operation and maintenance system.

[0055] It is worth noting that, such as Figure 3 As shown, based on instruction recognition, the central coordinator allocates data collection and risk assessment tasks according to the power equipment set and the real-time typhoon path. The corresponding intelligent agents execute the tasks and store the output of the intelligent agents in the database. The central coordinator assigns equipment damage information aggregation and analysis instructions to the equipment damage information aggregation and analysis intelligent agent. The equipment damage information aggregation and analysis intelligent agent reads the data of each intelligent agent from the database. Based on the real-time typhoon path and the predicted typhoon path, it predicts the affected power equipment. After selecting a power equipment set, it determines the expected failure sequence of the power equipment in the set and the predicted distance from the typhoon center to the location of each equipment. Combining the historical data of the equipment, it obtains the expected failure risk intensity of each equipment in the power equipment set and calculates the risk matching value between the typhoon path and the equipment failure prediction sequence. Then, it constructs a power equipment risk early warning model to calculate the risk early warning score of each power equipment set. After traversing all power equipment sets, it selects the power equipment set with the highest risk early warning score as the push result, determines the equipment monitoring and protection sequence, and pushes the early warning. The central coordinator assigns a report generation task to the equipment damage information aggregation and analysis intelligent agent. The equipment damage information aggregation and analysis intelligent agent summarizes the data, forms a report, and pushes the report to the operation and maintenance system through the communication interface.

[0056] In the aforementioned multi-agent collaborative power equipment management method, the first agent in the multi-agent collaborative architecture, through its fusion processing of multi-source typhoon prediction paths, helps alleviate the limitations of traditional meteorological data collection, which has a relatively singular coverage. Relying on the real-time acquisition capabilities of the third agent, it can, to some extent, improve the lag problem in equipment operation data collection under extreme weather conditions. The second agent, combining spatial matching mechanisms with dynamic operation data for comprehensive evaluation, improves the accuracy of identifying affected power equipment and optimizes the refinement of risk assessment, thereby alleviating the shortcomings of relatively coarse and static risk assessment in traditional models. The fourth agent, through multi-dimensional priority ranking and adaptive report generation, can promote closed-loop management from risk warning to disposal, improving the efficiency of emergency response. The overall multi-agent architecture, with its parallel processing, professional adaptation, and distributed fault tolerance characteristics, enhances the reliability of the power supply system and the intelligence level of emergency management under extreme weather conditions.

[0057] In an exemplary embodiment, a risk assessment is performed based on the equipment operation data of the power equipment in the power equipment set and the typhoon forecast path corresponding to the power equipment set to determine the risk warning value of the power equipment set. This includes: for each power equipment in the power equipment set, extracting features from the equipment operation data, equipment attribute information, and typhoon meteorological data of the power equipment to obtain the power equipment features of the power equipment; inputting the power equipment features of the power equipment into a logistic regression model to predict the risk intensity to obtain the fault risk intensity of the power equipment; and performing a risk assessment based on the fault risk intensity of each power equipment in the power equipment set and the typhoon forecast path corresponding to the power equipment set to determine the risk warning value of the power equipment set.

[0058] Among them, the characteristics of power equipment can be the core analytical dimensions for risk intensity prediction obtained after feature extraction, including but not limited to static characteristics, dynamic characteristics and environmental characteristics. Static characteristics include equipment type, installation age, design wind resistance level and geographical location; dynamic characteristics include operating load, maintenance records and real-time status data; environmental characteristics include typhoon path, wind speed and rainfall; and fault risk intensity can be the output result of risk intensity prediction, which is a quantitative value characterizing the probability of a single power equipment failing under the influence of the corresponding typhoon prediction path. The higher the value, the higher the equipment failure risk.

[0059] Optionally, the second intelligent agent first extracts three types of power equipment features—static, dynamic, and environmental—from equipment operation data, equipment attribute information, and typhoon meteorological data for each individual device within the power equipment set. Then, it completes the quantitative prediction of the fault risk intensity of the individual device through a pre-trained logistic regression model. Finally, it integrates the risk of the individual device into the overall risk warning value of the power equipment set by combining the risk matching value formula with the power equipment risk warning model.

[0060] In one embodiment, the average fault risk intensity of the power equipment in the power equipment set is calculated to obtain the risk matching degree between the power equipment set and the corresponding typhoon prediction path; for each power equipment in the power equipment set, the predicted moving speed of the typhoon when the typhoon center is closest to the power equipment under the typhoon prediction path corresponding to the power equipment set and the predicted distance between the typhoon center and the power equipment are determined; based on the predicted distance, predicted moving speed and risk matching degree, the risk score of the power equipment is determined; based on the risk score of each power equipment in the power equipment set, the risk warning value of the power equipment set is determined.

[0061] Among them, the risk matching degree can be the risk matching value between the typhoon prediction path and the set of power equipment; the predicted movement speed can be the expected movement rate when the typhoon center is closest to the target power equipment under the typhoon prediction path corresponding to the set of power equipment; and the prediction distance can be the minimum expected geographical distance between the typhoon center and the target power equipment under the typhoon prediction path corresponding to the set of power equipment.

[0062] Optionally, based on the typhoon's real-time path information and predicted typhoon path, the affected equipment is predicted, generating a set of power equipment corresponding to each path. An arbitrary set of power equipment is selected and denoted as E. c , of which E c Let E represent the c-th set of electrical equipment. c The expected failure sequence of the power equipment is obtained as UEC. i And the predicted distance between the typhoon center and the equipment location (TEC) i , among which, TEC i Indicates the distance from the typhoon center to the power equipment collection E. c The predicted distance of the location of the i-th device in the UEC i Indicates according to the set of power equipment E C The i-th affected device; calculate the set of power devices E. c The expected failure risk intensity PEC of the i-th device i For the power equipment set E c The expected failure risk intensity of each device is obtained by iterating through the arrival times of the typhoon. Binary labels are used as training targets, where 1 represents an actual failure in a specific historical typhoon event, and 0 represents no failure. It is worth noting that logistic regression can be used for training, inputting power equipment features and outputting the expected failure risk intensity. According to the formula R... c =(ΣPEC i The risk matching degree between the predicted typhoon path and the power equipment set is calculated using R / I; where R is the predicted path. c Represents the predicted typhoon path and the set of power equipment E c The risk matching degree between them, where I represents the set of power equipment E C The total number of devices in the system.

[0063] For example, a power equipment risk warning model can be constructed to determine the risk warning value of a set of power equipment. The power equipment risk warning model is defined as follows:

[0064]

[0065] Wherein, Sc represents the risk warning score of the power equipment set Ec, Rc represents the risk matching degree between the typhoon prediction path and the power equipment set Ec, TECi represents the predicted distance from the typhoon center to the location of the i-th equipment in the power equipment set Ec, v represents the speed at which the typhoon moves to the location of each equipment in the power equipment set Ec, I represents the total number of equipment in the power equipment set Ec, and w1 represents the weighting coefficient; it is worth noting that the weighting coefficient can be set according to information such as the intensity and speed of the typhoon.

[0066] In this embodiment, through multi-dimensional feature extraction, single-device risk quantification prediction, and comprehensive risk assessment of equipment sets, the risk of power equipment has been upgraded from qualitative judgment to quantitative analysis, from single dimension to multi-factor coupling, and from single-device assessment to cluster risk assessment. This solves the problems of single dimension, insufficient accuracy, and ambiguous results in traditional power equipment typhoon risk assessment, and improves the intelligence and precision of power equipment management.

[0067] In an exemplary embodiment, a target power equipment set is selected from multiple power equipment sets based on a risk warning value, and an equipment management report is generated based on the target power equipment set. This includes: selecting a target power equipment set whose risk warning value is greater than a warning threshold from multiple power equipment sets; if there are at least two target power equipment sets, selecting target power equipment from at least two target power equipment sets based on the number of times the power equipment appears in at least two target power equipment sets; sorting the power equipment in the target power equipment sets according to the risk time of the power equipment in the target power equipment sets to obtain the power equipment sequence corresponding to the target power equipment set, where the risk time of the power equipment refers to the time when the typhoon center is closest to the power equipment; and generating an equipment management report based on the target power equipment and the power equipment sequences corresponding to the at least two target power equipment sets respectively.

[0068] The warning threshold can be a preset risk threshold used to screen high-risk sets. When the risk warning value exceeds the threshold, the set is determined to be under key monitoring. The target power equipment can be a set of power equipment whose risk warning value is greater than the warning threshold selected from multiple sets of power equipment. The power equipment sequence can be a sequence formed by sorting the equipment in the target set according to the risk time.

[0069] Optionally, under the command and scheduling of the central coordinator, the intelligent agent for aggregating and analyzing equipment damage information first filters out the target power equipment set based on the risk warning value and warning threshold, then counts the frequency of equipment occurrence for multiple target sets to determine the target power equipment, then sorts the equipment in each target set according to the risk time to generate a power equipment sequence, and finally integrates all data to form an equipment management report and pushes it to the operation and maintenance system. It is worth noting that if there is only one target power equipment set, the equipment management report for the target power equipment set is generated directly; alternatively, the power equipment set associated with the highest risk warning value can be selected to generate the equipment management report, but this embodiment does not limit this.

[0070] In one embodiment, generating an equipment management report based on the target power equipment and the power equipment sequences corresponding to at least two sets of target power equipment further includes: for each power equipment in the power equipment set, using a second intelligent agent to determine the typhoon event characteristics when the typhoon center is closest to the power equipment based on typhoon meteorological data, and determining the historical typhoons associated with the power equipment based on the typhoon event characteristics; for each power equipment in the power equipment set, obtaining the affected time window of the power equipment under the associated historical typhoons, and constructing a risk time window set corresponding to the power equipment set based on the obtained affected time windows; and generating an equipment management report based on the target power equipment, the power equipment sequences corresponding to at least two sets of target power equipment, and the risk time window set corresponding to each power equipment set.

[0071] Among them, the typhoon event characteristics can be the core meteorological parameters when the typhoon center is closest to the power equipment under the typhoon prediction path, including but not limited to the typhoon's movement speed, instantaneous wind speed, rainfall, and wind circle radius; historical typhoons can be past typhoons that are highly matched with the current typhoon event characteristics and selected from the historical typhoon database; the affected time window can be the specific period when the power equipment is judged to be at high risk of damage under the influence of its associated historical typhoons.

[0072] Optionally, the set of power equipment is traversed to obtain the risk warning score S for the set of power equipment. rr = 1, 2, ..., R, where R represents the total number of generated power equipment sets; based on the risk warning scores of the power equipment sets, Z sequences with risk warning scores greater than the preset risk warning score threshold are selected as abnormal power equipment sets, where Z represents the preset number of abnormal power equipment sets. Equipment monitoring and protection sequences are determined to push warnings to the operation and maintenance system; the central coordinator distributes equipment damage information aggregation and analysis instructions and report generation instructions to the equipment damage information aggregation and analysis intelligent agent. The equipment damage information aggregation and analysis intelligent agent analyzes the risk warning score data of the abnormal power equipment sets to form a report. The method for forming the report can be: the equipment appearing in the abnormal power equipment set is {G1, G2, ..., G...} h , ..., G H}, where H represents the total number of power devices in the abnormal power device set, and G h Let H represent the h-th device in the set of abnormal power equipment. Let {L1, L2, ..., L...} be the number of times the H devices in the set of abnormal power equipment appear. h , ..., L H The device that appears most frequently among the H devices is selected as the priority reinforcement device (i.e., the target power device). After the priority reinforcement device is confirmed to be reinforced, it is removed from the H devices. After the priority reinforcement device is removed, the risk warning score is re-analyzed according to the power device risk warning model until the risk warning score of each power device set is less than or equal to the risk warning score threshold.

[0073] It is worth noting that when the central coordinator recognizes the typhoon path update instruction, it obtains the latest path data from the meteorological intelligent agent, reads the historical data of the equipment from the database, constructs a set of predicted high-risk time windows corresponding to the target equipment based on the set of power equipment and the real-time typhoon path, stores the output content of the predicted intelligent agent of the affected equipment in the database, and notifies the central coordinator.

[0074] Based on the list of predicted damaged equipment priorities, construct the set of predicted high-risk time windows (i.e., affected time windows) T corresponding to the i-th power equipment. i ={T i1 T i2 , ..., T ik , ..., T iK}, where T ikThis indicates that, based on historical data analysis, the time window in which the i-th power device is identified as having a predicted high risk of damage during the k-th historical typhoon event is determined, where K represents the total number of historical typhoon events in which the power device is detected as having a predicted high risk of damage; the central coordinator assigns data collection tasks to the damaged equipment information acquisition agent based on the power equipment set. The damaged equipment information acquisition agent prioritizes collecting data from the equipment with the highest prediction priority, and simultaneously collects data from suddenly damaged equipment, marking them as the set of unpredictable damaged equipment, and acquiring related business data. After completion, the damaged equipment information acquisition agent stores the output content in the database; the damaged equipment information acquisition agent prioritizes collecting data from the power equipment with the highest prediction priority, and simultaneously collects data from suddenly damaged equipment not included in the predicted damaged equipment priority list, including historical operating status data and video data, marking them as unpredictable damaged equipment and outputting the set of unpredictable damaged equipment. Among them, the video data includes videos reflecting the status of the unpredictable damaged equipment itself and videos of the surrounding on-site environment of the unpredictable damaged power equipment; for the marked unpredictable damaged equipment, the business system data associated with it is obtained in real time.

[0075] In this embodiment, by stratified screening of high-risk equipment sets and individual equipment, constructing control sequences according to risk time, and integrating data to generate professional operation and maintenance reports, the risk of power equipment in typhoon scenarios has been upgraded from group assessment to individual focus and from disordered control to time-series disposal, thereby improving the intelligence, precision and orderliness of power equipment management under extreme weather conditions.

[0076] To more comprehensively demonstrate this solution, this embodiment presents an optional approach to a multi-agent collaborative power equipment management method, including:

[0077] 1. Obtain typhoon meteorological data through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon.

[0078] 2. For each typhoon forecast path, the second intelligent agent determines the power equipment affected by the typhoon forecast path from among the multiple power equipment based on the equipment attribute information of each power equipment, and obtains the set of power equipment corresponding to the typhoon forecast path.

[0079] 3. For each set of power equipment, use a third-party intelligent agent to obtain the equipment operation data of each power equipment in the set;

[0080] 4. For each set of power equipment, through the second intelligent agent, feature extraction is performed on the equipment operation data, equipment attribute information and typhoon meteorological data of each power equipment in the set to obtain the power equipment features of the power equipment;

[0081] 5. Input the characteristics of the power equipment into the logistic regression model to predict the risk intensity and obtain the fault risk intensity of the power equipment;

[0082] 6. Conduct a risk assessment based on the fault risk intensity of each power device in the power equipment set and the typhoon forecast path corresponding to the power equipment set, and determine the risk warning value of the power equipment set;

[0083] 7. Using a fourth intelligent agent, select a set of target power equipment whose risk warning value is greater than the warning threshold from multiple sets of power equipment;

[0084] 8. In the case that there are at least two target sets of electrical equipment, select target electrical equipment from the at least two target sets based on the number of times the electrical equipment appears in the at least two target sets;

[0085] 9. Sort the power equipment in the target power equipment set according to the risk time of the power equipment in the target power equipment set to obtain the power equipment sequence corresponding to the target power equipment set. The risk time of the power equipment refers to the time when the typhoon center is closest to the power equipment.

[0086] 10. Generate an equipment management report based on the target power equipment and the power equipment sequences corresponding to at least two sets of target power equipment. The equipment management report is used for the management of power equipment.

[0087] The specific process of the above steps can be found in the description of the above method embodiments. The implementation principle and technical effect are similar, and will not be repeated here.

[0088] 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.

[0089] Based on the same inventive concept, this application also provides a multi-agent collaborative power equipment management device for implementing the multi-agent collaborative power equipment management method described above. The solution provided by this device is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the multi-agent collaborative power equipment management device provided below can be found in the limitations of the multi-agent collaborative power equipment management method described above, and will not be repeated here.

[0090] In one exemplary embodiment, such as Figure 4 As shown, a multi-agent collaborative power equipment management device is provided, comprising: an acquisition module 41, a matching module 42, a prediction module 43, and a generation module 44, wherein:

[0091] The acquisition module 41 is used to acquire typhoon meteorological data through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon.

[0092] Matching module 42 is used to determine the power equipment affected on the typhoon prediction path from multiple power equipment through the second intelligent agent for each typhoon prediction path, based on the equipment attribute information of each power equipment, and obtain the set of power equipment corresponding to the typhoon prediction path.

[0093] The acquisition module 41 is also used to obtain the equipment operation data of each power device in the power device set using a third intelligent agent for each power device set;

[0094] Prediction module 43 is used to determine the risk warning value of each power equipment set by using a second intelligent agent to conduct risk assessment based on the equipment operation data of the power equipment in the power equipment set and the typhoon prediction path corresponding to the power equipment set.

[0095] The generation module 44 is used to filter out the target power equipment set from multiple power equipment sets according to the risk warning value through the fourth intelligent agent, and generate an equipment management report based on the target power equipment set. The equipment management report is used for the management of power equipment.

[0096] In one embodiment, the prediction module 43 is further configured to:

[0097] For each power device in the power equipment set, feature extraction is performed on the equipment operation data, equipment attribute information, and typhoon meteorological data to obtain the power equipment features. The power equipment features are then input into a logistic regression model to predict the risk intensity and obtain the fault risk intensity of the power equipment. Based on the fault risk intensity of each power device in the power equipment set and the typhoon prediction path corresponding to the power equipment set, a risk assessment is performed to determine the risk warning value of the power equipment set.

[0098] In one embodiment, the prediction module 43 is further configured to:

[0099] The average fault risk intensity of the power equipment in the power equipment set is calculated to obtain the risk matching degree between the power equipment set and the corresponding typhoon prediction path. For each power equipment in the power equipment set, the predicted moving speed of the typhoon when the typhoon center is closest to the power equipment and the predicted distance between the typhoon center and the power equipment are determined under the typhoon prediction path corresponding to the power equipment set. Based on the predicted distance, predicted moving speed and risk matching degree, the risk score of the power equipment is determined. Based on the risk score of each power equipment in the power equipment set, the risk warning value of the power equipment set is determined.

[0100] In one embodiment, the generation module 44 is further configured to:

[0101] From multiple sets of power equipment, select the target power equipment set whose risk warning value is greater than the warning threshold; if there are at least two target power equipment sets, select target power equipment from the at least two target power equipment sets based on the frequency of occurrence of the power equipment in the at least two target power equipment sets; sort the power equipment in the target power equipment sets according to the risk time of the power equipment in the target power equipment sets to obtain the power equipment sequence corresponding to the target power equipment sets, where the risk time of the power equipment refers to the time when the typhoon center is closest to the power equipment; generate an equipment management report based on the target power equipment and the power equipment sequences corresponding to the at least two target power equipment sets respectively.

[0102] In one embodiment, the generation module 44 is further configured to:

[0103] For each power device in the power equipment set, a second intelligent agent determines the typhoon event characteristics when the typhoon center is closest to the power device based on typhoon meteorological data, and identifies the historical typhoons associated with the power device based on the typhoon event characteristics. For each power device in the power equipment set, the affected time window under the associated historical typhoon is obtained, and a risk time window set corresponding to the power equipment set is constructed based on the obtained affected time windows. Based on the target power device, the power equipment sequence corresponding to at least two target power equipment sets, and the risk time window set corresponding to each power equipment set, an equipment management report is generated.

[0104] In one embodiment, the matching module 44 is further configured to:

[0105] Based on the installation location information of multiple power devices, the power devices that will be covered by the typhoon along the typhoon's predicted path are identified from among the multiple power devices. Based on the device attribute characteristics, the power devices that will be affected by the typhoon along the predicted typhoon path are screened from the power devices covered by the typhoon. The device attribute characteristics are used to reflect the risk resistance capability of the power devices.

[0106] In one embodiment, the acquisition module 41 is further configured to:

[0107] The second intelligent agent determines the typhoon event characteristics at the location of each power device in the power equipment set based on typhoon meteorological data, and identifies at least one historical typhoon associated with each power device based on the typhoon event characteristics. The second intelligent agent also determines the equipment priority of each power device in the power equipment set based on the fault records of each power device under historical typhoons. The third intelligent agent collects the equipment operation data of each power device in the power equipment set according to the equipment priority of the power devices in the power equipment set.

[0108] The modules in the aforementioned multi-agent collaborative power equipment management device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0109] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores power equipment management data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a multi-agent collaborative power equipment management method.

[0110] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface 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 interface. 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 in the non-volatile storage media. The input / output interface is 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 multi-agent collaborative power equipment management method. The display unit is used to form a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0111] Those skilled in the art will understand that Figure 5 and Figure 6The 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.

[0112] 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.

[0113] 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.

[0114] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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 method for managing power equipment through multi-agent collaboration, characterized in that, The method includes: Typhoon meteorological data is obtained through a first intelligent agent, and the typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon. For each typhoon forecast path, a second intelligent agent determines the power equipment affected on the typhoon forecast path from the multiple power equipment based on their respective equipment attribute information, thereby obtaining the set of power equipment corresponding to the typhoon forecast path. For each set of power equipment, a third intelligent agent is used to obtain the equipment operation data of each power equipment in the set of power equipment; For each set of power equipment, the second intelligent agent performs a risk assessment based on the equipment operation data of the power equipment in the set and the typhoon prediction path corresponding to the set of power equipment, and determines the risk warning value of the set of power equipment. The fourth intelligent agent filters out the target set of power equipment from the multiple sets of power equipment based on the risk warning value, and manages the power equipment based on the target set of power equipment.

2. The method according to claim 1, characterized in that, The step of conducting a risk assessment based on the equipment operation data of the power equipment in the power equipment set and the typhoon forecast path corresponding to the power equipment set, and determining the risk warning value of the power equipment set, includes: For each power device in the power equipment set, feature extraction is performed on the equipment operation data, equipment attribute information, and typhoon meteorological data of the power device to obtain the power equipment features of the power device. The power equipment characteristics of the power equipment are input into a logistic regression model to predict the risk intensity, thereby obtaining the fault risk intensity of the power equipment. Risk assessment is performed based on the fault risk intensity of each power device in the power equipment set and the typhoon prediction path corresponding to the power equipment set, and the risk warning value of the power equipment set is determined.

3. The method according to claim 2, characterized in that, The step of determining the risk warning value of the power equipment set by performing a risk assessment based on the fault risk intensity of each power equipment in the power equipment set and the typhoon prediction path corresponding to the power equipment set includes: The average fault risk intensity of the power equipment in the set of power equipment is calculated to obtain the risk matching degree between the set of power equipment and the corresponding typhoon prediction path; For each power device in the power device set, determine the predicted moving speed of the typhoon when its center is closest to the power device under the typhoon prediction path corresponding to the power device set, and the predicted distance between the typhoon center and the power device; The risk score of the power equipment is determined based on the predicted spacing, the predicted moving speed, and the risk matching degree. Based on the risk score of each power device in the power equipment set, a risk warning value for the power equipment set is determined.

4. The method according to claim 1, characterized in that, The step of selecting a target set of power equipment from the plurality of power equipment sets based on risk warning values, and managing the power equipment based on the target set of power equipment, includes: Select a target set of power equipment whose risk warning value is greater than the warning threshold from multiple sets of power equipment; In the presence of at least two target sets of power equipment, target power equipment is selected from the at least two target sets of power equipment based on the number of times each power equipment appears in the at least two target sets of power equipment. The power devices in the target power device set are sorted according to their risk time to obtain the power device sequence corresponding to the target power device set. The risk time of the power device refers to the time when the typhoon center is closest to the power device. Based on the target power equipment and the power equipment sequences corresponding to the at least two sets of target power equipment, an equipment management report is generated, which is used for the management of power equipment.

5. The method according to claim 4, characterized in that, The step of generating an equipment management report based on the target power equipment and the power equipment sequences corresponding to the at least two sets of target power equipment respectively further includes: For each power device in the set of power devices, the second intelligent agent determines the typhoon event characteristics when the typhoon center is closest to the power device based on the typhoon meteorological data, and determines the historical typhoons associated with the power device based on the typhoon event characteristics. For each power device in the power equipment set, obtain the affected time window of the power device under the associated historical typhoon, and construct the risk time window set corresponding to the power equipment set based on the obtained affected time window; An equipment management report is generated based on the target power equipment, the power equipment sequences corresponding to the at least two sets of target power equipment, and the risk time window set corresponding to each set of power equipment.

6. The method according to any one of claims 1 to 5, characterized in that, The equipment attribute information includes installation location information and equipment attribute characteristics. The step of determining the power equipment affected by the typhoon's predicted path from among the multiple power equipment based on their respective equipment attribute information includes: Based on the installation location information of the plurality of power devices, determine the power devices covered by the typhoon on the typhoon's predicted path from among the plurality of power devices; Based on equipment attribute characteristics, power equipment affected by the predicted typhoon path is selected from the power equipment covered by the typhoon. These equipment attribute characteristics reflect the risk resistance capability of the power equipment.

7. The method according to any one of claims 1 to 5, characterized in that, The step of obtaining the equipment operation data of each power device in the power equipment set using a third intelligent agent also includes: The second intelligent agent determines the typhoon event characteristics of the current typhoon at the location of each power device in the power device set based on the typhoon meteorological data, and determines at least one historical typhoon associated with each power device based on the typhoon event characteristics. The second intelligent agent determines the equipment priority of each power device in the power device set based on the fault records of each power device under the historical typhoons. The third intelligent agent collects the equipment operation data of each power device in the power device set according to the equipment priority of the power devices in the set.

8. A multi-agent collaborative power equipment management device, characterized in that, The device includes: The acquisition module is used to acquire typhoon meteorological data through the first intelligent agent. The typhoon meteorological data includes multiple typhoon prediction paths corresponding to the typhoon. The matching module is used to determine the power equipment affected on the typhoon prediction path for each typhoon prediction path through a second intelligent agent based on the equipment attribute information of multiple power equipment, and obtain the set of power equipment corresponding to the typhoon prediction path. The acquisition module is further configured to obtain, for each of the power equipment sets, the equipment operation data of each power equipment in the power equipment set using a third intelligent agent; The prediction module is used to perform risk assessment on each of the power equipment sets by means of the second intelligent agent, based on the equipment operation data of the power equipment in the power equipment set and the typhoon prediction path corresponding to the power equipment set, and to determine the risk warning value of the power equipment set. The generation module is used to filter out a target set of power equipment from the multiple sets of power equipment based on the risk warning value through a fourth intelligent agent, and generate an equipment management report based on the target set of power equipment. The equipment management report is used for the management of power equipment.

9. 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 7.

10. 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 7.

Images