Emergency disposal method and device, computer equipment, storage medium and computer program product

By pre-processing and abnormal detection of power, meteorological and satellite data in power grid scenarios, and using emergency response scheduling models to optimize resources and paths, the problem of low emergency response efficiency in the power industry is solved, and efficient emergency response and safe operation of power grid scenarios is achieved .

CN119066562APending Publication Date: 2024-12-03GUANGDONG POWER GRID CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202411001660.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-12-03

AI Technical Summary

Technical Problem

Traditional manual monitoring and response mechanisms are difficult to meet the rapidly changing needs of the power industry, especially in extreme weather events, which is difficult to quickly identify and respond to power grid abnormalities, resulting in low emergency response efficiency.

Method used

By preprocessing, abnormal detection and event classification of power data, meteorological data and satellite remote sensing data of power grid scenarios, the trained emergency response scheduling model is used to optimize resource configuration and path planning, generate target emergency response information, and evaluate and update it in real time , to improve emergency response speed and resource utilization.

Benefits of technology

It realizes rapid abnormality capture and classification of power grid scenarios, improves emergency response efficiency, ensures safe operation of the power grid, and improves the accuracy and efficiency of emergency response through dynamic optimization of emergency strategies and resource allocation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119066562A_ABST
    Figure CN119066562A_ABST
Patent Text Reader

Abstract

The invention relates to an emergency disposal method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps of performing data preprocessing on current power data of a power grid scene, current meteorological data of a meteorological scene and current monitoring data of satellite remote sensing associated with the power grid scene to obtain processed power data, processed meteorological data and processed monitoring data; performing anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain an anomaly detection result for the power grid scene; if the abnormity detection result represents abnormity, abnormal event classification processing is carried out on the processed power data, the processed meteorological data and the processed monitoring data, and abnormal event information corresponding to the abnormity detection result is obtained; and determining target emergency disposal information of the power grid scene according to the abnormal event information and the abnormal detection result. By adopting the method, the emergency disposal efficiency of the power grid scene can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an emergency response method, apparatus, computer equipment, storage medium and computer program product. Background Art

[0002] With the increasing complexity of power grids and the increase in extreme weather events, the power industry faces more uncertainties and challenges. Traditional manual monitoring and response mechanisms are unable to meet the rapidly changing needs of the power industry.

[0003] In recent years, with the continuous development of artificial intelligence technology, artificial intelligence technology can quickly identify and analyze massive data, quickly locate anomalies when they occur, and assist in decision-making. Therefore, it is crucial to introduce artificial intelligence technology to enhance emergency response in power grid scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide an emergency response method, device, computer equipment, computer-readable storage medium and computer program product that can improve the efficiency of emergency response in power grid scenarios in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides an emergency response method. The method comprises:

[0006] Preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data;

[0007] Performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain an anomaly detection result for the power grid scenario;

[0008] If it is detected that the abnormal detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result;

[0009] According to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario is determined.

[0010] In one embodiment, determining target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result includes:

[0011] Acquire preset emergency handling information that matches the abnormal event information and the abnormal detection result;

[0012] By using the trained emergency response scheduling model, the resource configuration information in the preset emergency response information is optimized to obtain optimized emergency response information;

[0013] The trained emergency response scheduling model is used to perform path optimization processing on the path planning information in the optimized emergency response information to obtain the target emergency response information.

[0014] In one of the embodiments, after determining the target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result, the method further includes:

[0015] Obtaining an immediate evaluation result of the target emergency handling information according to the emergency response speed, resource utilization rate, and abnormal event control speed within the first period of time after the target emergency handling information is executed in the power grid scenario;

[0016] Obtaining a long-term evaluation result of the target emergency disposal information according to power operation data and environmental data within a second time period after executing the target emergency disposal information according to the power grid scenario; the second time period is greater than the first time period;

[0017] The preset emergency response information and the trained emergency response scheduling model are updated according to the immediate evaluation result and the long-term evaluation result.

[0018] In one embodiment, performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain anomaly detection results for the power grid scenario includes:

[0019] Screening out candidate abnormal data exceeding a preset data threshold from the processed power data, the processed meteorological data and the processed monitoring data;

[0020] The candidate abnormal data and the abnormal data features corresponding to the candidate abnormal data are input into a pre-trained abnormality detection model to obtain the abnormality detection result.

[0021] In one embodiment, the processed power data, the processed meteorological data, and the processed monitoring data are subjected to abnormal event classification processing to obtain abnormal event information corresponding to the abnormal detection result, including:

[0022] Inputting the processed power data, the processed meteorological data and the processed monitoring data into a pre-trained event classification model to obtain the abnormal event category of the abnormal detection result;

[0023] Based on the knowledge base of the power grid scenario, performing anomaly evaluation on the anomaly detection result to obtain a handling priority of the anomaly detection result;

[0024] The abnormal event category and the handling priority are used as the abnormal event information.

[0025] In one embodiment, data preprocessing is performed on current power data of a power grid scenario, current meteorological data of a meteorological scenario, and current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data, including:

[0026] Performing data cleaning on the current power data, the current meteorological data, and the current monitoring data to obtain cleaned power data, cleaned meteorological data, and cleaned monitoring data;

[0027] Feature engineering processing is performed on the cleaned power data, the cleaned meteorological data and the cleaned monitoring data to obtain the processed power data, the processed meteorological data and the processed monitoring data.

[0028] In a second aspect, the present application also provides an emergency disposal device. The device comprises:

[0029] A data acquisition module is used to pre-process the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data;

[0030] An anomaly detection module, used to perform anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain an anomaly detection result for the power grid scenario;

[0031] An event classification module, configured to perform abnormal event classification processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result if the abnormal detection result indicates an abnormality;

[0032] The emergency handling module is used to determine the target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result.

[0033] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0034] Preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data;

[0035] Performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain an anomaly detection result for the power grid scenario;

[0036] If it is detected that the abnormal detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result;

[0037] According to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario is determined.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0039] Preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data;

[0040] Performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain an anomaly detection result for the power grid scenario;

[0041] If it is detected that the abnormal detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result;

[0042] According to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario is determined.

[0043] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0044] Preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data;

[0045] Performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain an anomaly detection result for the power grid scenario;

[0046] If it is detected that the abnormal detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result;

[0047] According to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario is determined.

[0048] The above-mentioned emergency handling method, device, computer equipment, storage medium and computer program product perform data preprocessing on the current power data of the power grid scene, the current meteorological data of the meteorological scene and the current monitoring data of satellite remote sensing associated with the power grid scene to obtain processed power data, processed meteorological data and processed monitoring data; perform abnormal detection processing on the processed power data, processed meteorological data and processed monitoring data to obtain abnormal detection results for the power grid scene; if the abnormal detection result represents an abnormality, perform abnormal event classification processing on the processed power data, processed meteorological data and processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result; determine the target emergency handling information of the power grid scene based on the abnormal event information and the abnormal detection result. By adopting this method, it is possible to capture anomalies from real-time data from multiple sources, quickly classify abnormal events and initiate corresponding target emergency handling information, thereby ensuring the high efficiency of emergency response to the power grid scene and providing guarantee for the safe operation of the power grid scene. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 An application environment diagram of an emergency response method in an embodiment;

[0050] Figure 2 A schematic diagram of a flow chart of an emergency response method in one embodiment;

[0051] Figure 3 A schematic diagram of a flow chart of a step of determining target emergency handling information for a power grid scenario in one embodiment;

[0052] Figure 4 A schematic flow chart of an emergency response method in another embodiment;

[0053] Figure 5 is a structural block diagram of an emergency response device in one embodiment;

[0054] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0055] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] 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, stored data, displayed data, 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 relevant data must comply with relevant regulations.

[0057] The emergency response method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, various power equipment in the power grid scene 101, equipment in the meteorological scene 102 (such as a weather station), and the satellite remote sensing platform 103 communicate with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the server 104 can be implemented as an independent server or a server cluster consisting of multiple servers.

[0058] In one embodiment, Figure 2 As shown, an emergency disposal method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0059] Step S201, preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data.

[0060] Among them, current power data refers to the power data of the real-time operation of power equipment in the power grid scenario. Current meteorological data refers to real-time meteorological data; for example, current meteorological data may include weather, temperature, customs, wind direction, humidity, etc. Current monitoring data refers to satellite data measured in real time based on satellite remote sensing technology.

[0061] Specifically, the server can obtain the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario in real time. It can also obtain the current data of other scenarios associated with the power grid scenario, and then perform pre-processing such as data cleaning, feature engineering, and quality inspection on the acquired current power data, current meteorological data, and current monitoring data, and finally obtain processed power data, processed meteorological data, and processed monitoring data, providing multi-source and reliable data for subsequent analysis.

[0062] Step S202, performing anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain anomaly detection results for the power grid scenario.

[0063] Among them, the anomaly detection result refers to the information describing the abnormal situation in the power grid scenario.

[0064] Specifically, the server can filter out abnormal data from processed power data, processed meteorological data, and processed monitoring data through anomaly detection algorithms. The server can also continuously monitor the devices corresponding to these abnormal data through the stream processing framework to obtain more data streams; then, based on the abnormal data and the data streams obtained through continuous monitoring, analyze the anomaly detection results of the power grid scenario. In practical applications, the stream processing framework can be Apache Kafka (an open source stream processing software platform), Apache Storm (an open source distributed real-time computing system that can be used to process large-scale real-time data streams) or Spark Streaming (a streaming computing framework for processing real-time data streams).

[0065] Step S203: If it is detected that the abnormal detection result indicates an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result.

[0066] Among them, abnormal event information is used to describe the type, level, severity and other aspects of abnormal events; abnormal event information includes abnormal category, emergency response priority, abnormal severity, resource demand information, etc.

[0067] Specifically, if the abnormal detection result is detected to be normal, the server can continue to collect current data of power grid scenes, meteorological scenes and satellite remote sensing and perform abnormal detection. If the abnormal detection result is detected to be abnormal, the server can further accurately determine the specific abnormal event information of the abnormal detection result through the pre-trained event classification model and the knowledge base or expert base of the power grid scene.

[0068] Step S204: determining target emergency handling information for the power grid scenario based on the abnormal event information and the abnormal detection result.

[0069] The target emergency disposal information refers to the content of the emergency measures to be taken when an abnormal event occurs in the power grid scenario. For example, the target application disposal information can be a disposal strategy for abnormal events, and the target application disposal information includes but is not limited to personnel scheduling, resource allocation, communication process, etc.

[0070] Specifically, based on the event characteristics of the abnormal event information and the abnormal detection results, the server screens out an emergency response plan that meets the characteristics of the event from multiple preset emergency response plans, and then adaptively optimizes the emergency response plan through the trained emergency disposal scheduling model to obtain an emergency response plan that fits the actual abnormal situation of the power grid scenario, and finally obtains the target emergency disposal information.

[0071] Furthermore, the server can also monitor the execution of the target emergency disposal information in the power grid scene in real time through the Internet of Things devices, mobile terminals and other monitoring means in the power grid scene, including task progress, personnel location, resource usage, etc. If any deviation or unexpected change is detected during the execution process, the trained emergency disposal scheduling model is immediately notified to update the target emergency disposal information online, which effectively improves the accuracy of the target emergency disposal information.

[0072] In actual applications, the server can also be connected to the communication platform to intelligently assist in coordinating the cooperation between different departments, such as dispatch, logistics, technical support, etc., to ensure seamless connection of all aspects of emergency response. Through the integrated communication platform, it ensures smooth communication between the emergency response team, on-site staff, logistics support, and senior management.

[0073] In the above emergency handling method, data preprocessing is performed on the current power data of the power grid scene, the current meteorological data of the meteorological scene, and the current monitoring data of satellite remote sensing associated with the power grid scene to obtain processed power data, processed meteorological data, and processed monitoring data; abnormality detection processing is performed on the processed power data, processed meteorological data, and processed monitoring data to obtain abnormality detection results for the power grid scene; if the abnormality detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, processed meteorological data, and processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result; based on the abnormal event information and the abnormality detection result, the target emergency handling information of the power grid scene is determined. By adopting this method, anomalies can be captured from real-time data from multiple sources, abnormal events can be quickly classified, and corresponding target emergency handling information can be initiated, ensuring the efficiency of emergency response to the power grid scene and providing a guarantee for the safe operation of the power grid scene.

[0074] In one embodiment, Figure 3 As shown, the above step S204 determines the target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result, which specifically includes the following contents:

[0075] Step S301, obtaining preset emergency handling information that matches the abnormal event information and the abnormal detection result.

[0076] Specifically, the server can pre-set multiple emergency response plans, or set historical emergency handling information as an emergency response plan. The server selects an emergency response plan that matches the abnormal event information and abnormal detection results from the stored multiple emergency response plans, and uses it as the preset emergency handling information.

[0077] In actual applications, the server can filter out matching preset emergency response information based on the abnormal event category and abnormal severity in the abnormal event information, as well as the impact range of abnormal data in the abnormal detection results. The preset emergency response information includes but is not limited to personnel scheduling, resource allocation, communication process, etc.

[0078] Step S302: performing configuration optimization processing on the resource configuration information in the preset emergency response information through the trained emergency response scheduling model to obtain optimized emergency response information.

[0079] Among them, the emergency response dispatch model refers to an artificial intelligence (AI) model used to dynamically optimize emergency response information. In practical applications, the emergency response dispatch model focuses on achieving the optimal allocation and dispatch of resources in power grid scenarios, covering multiple levels such as human resources, material supplies, and financial resources. By integrating external information such as real-time traffic conditions and weather forecasts, dynamic path planning and logistics optimization technology can generate efficient task allocation plans and response paths and other emergency response content, significantly shortening the time for resources to arrive at the scene. In addition, the emergency response dispatch model also has the ability to dynamically adjust strategies to ensure that emergency response information can flexibly respond to the evolution of events, continuously optimize the response effect, and improve the overall response speed and resource utilization efficiency.

[0080] Specifically, the server can input the processed power data into the trained emergency response scheduling model. The trained emergency response scheduling model optimizes the resource configuration information in the preset emergency response information according to the processed power data, including optimizing the resource configuration information such as manpower, materials, and resources, and outputs the optimized emergency response information.

[0081] Step S303, using the trained emergency response scheduling model, performing path optimization processing on the path planning information in the optimized emergency response information to obtain target emergency response information.

[0082] Specifically, the server inputs the processed meteorological data into the trained emergency response scheduling model. The trained emergency response scheduling model further optimizes the path planning information in the optimized emergency response information based on the processed meteorological data to obtain the optimal path planning information and finally output the target emergency response information.

[0083] In this embodiment, the resource configuration information in the preset emergency disposal information is optimized through the trained emergency disposal scheduling model, which improves the resource utilization rate and ensures that the resources in the emergency disposal process are efficiently and fully utilized. Through the trained emergency disposal scheduling model, the path planning information in the optimized emergency disposal information is optimized through the path optimization processing, and the weather and other climate factors are combined to optimize the traffic path of the emergency disposal, which effectively shortens the emergency response time and improves the emergency disposal efficiency of the power grid scenario.

[0084] In one embodiment, in the above step S204, after determining the target emergency disposal information of the power grid scenario based on the abnormal event information and the abnormal detection results, it also includes: obtaining an immediate evaluation result of the target emergency disposal information based on the emergency response speed, resource utilization, and abnormal event control speed within a first time period after the power grid scenario executes the target emergency disposal information; obtaining a long-term evaluation result of the target emergency disposal information based on the power operation data and environmental data within a second time period after the power grid scenario executes the target emergency disposal information; the second time period is greater than the first time period; and updating the preset emergency disposal information and the trained emergency disposal scheduling model based on the immediate evaluation results and the long-term evaluation results.

[0085] Among them, the immediate evaluation results are used to reflect the short-term treatment effect of the target emergency disposal information on abnormal events in the power grid scenario. The long-term evaluation results are used to reflect the long-term impact of the target emergency disposal information on abnormal events in the power grid scenario.

[0086] Specifically, after the power grid scenario executes the target emergency disposal information, the server can also collect the execution progress of the power grid scenario to evaluate the immediate effect and long-term effect of the target emergency disposal information. The server can collect the emergency response speed, resource utilization rate, abnormal event control speed within the first time period after the power grid scenario executes the target emergency disposal information, as well as the power operation data and environmental data within the second time period; wherein the first time period is much shorter than the second time period, for example, the first time period can be one week, and the second time period can be one month. The server analyzes and obtains the immediate evaluation results of the target emergency disposal information based on the immediate evaluation indicators such as the emergency response speed, resource utilization rate, and abnormal event control speed; and analyzes and obtains the long-term evaluation results of the target emergency disposal information based on the long-term evaluation indicators such as the power operation data and environmental data. The server updates and improves the preset emergency disposal information based on the immediate evaluation results and the long-term evaluation results, which can be to add or modify the emergency disposal process, resource configuration information and communication protocol; and can also retrain or adjust the trained emergency disposal scheduling model based on the immediate evaluation results and the long-term evaluation results.

[0087] Furthermore, the server can also construct a knowledge graph of the power grid scenario based on the target emergency response information, immediate evaluation results and long-term evaluation results, and continuously update and improve the knowledge graph based on the target emergency response information, immediate evaluation results and long-term evaluation results obtained through subsequent processing, and associate the knowledge graph with the trained emergency response scheduling model to provide richer knowledge for the trained emergency response scheduling model through the knowledge graph, improve the ability of the trained emergency response scheduling model to optimize emergency response information, and thus improve the accuracy of the target emergency response information output by the trained emergency response scheduling model.

[0088] In this embodiment, the preset emergency response information and the trained emergency response scheduling model are updated according to the immediate evaluation results within the first time period and the long-term evaluation results within the second time period after the power grid scenario executes the target emergency response information, thereby achieving continuous improvement of the preset emergency response information and the emergency response scheduling model, which helps to improve the accuracy of the target emergency response information obtained by subsequent processing, thereby improving the emergency response effect after the power grid scenario executes the target emergency response information.

[0089] In one embodiment, the above step S202 performs anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain anomaly detection results for the power grid scenario, which specifically include the following contents: screening out candidate anomaly data exceeding a preset data threshold from the processed power data, the processed meteorological data and the processed monitoring data; inputting the candidate anomaly data and the abnormal data features corresponding to the candidate anomaly data into a pre-trained anomaly detection model to obtain anomaly detection results.

[0090] The anomaly detection model can be constructed by an anomaly detection algorithm. For example, the anomaly detection model can be constructed based on anomaly detection algorithms such as Isolation Forest or Local Outlier Factor.

[0091] The preset data threshold is used to roughly identify abnormal data points. The preset data threshold includes abnormal power data threshold, abnormal meteorological data threshold and abnormal monitoring data threshold.

[0092] Specifically, the server can set data thresholds according to historical abnormal power data, historical abnormal meteorological data, and historical abnormal monitoring data, and the server obtains a preset data threshold. The server can also train the anomaly detection model to be trained based on the historical abnormal power data, historical abnormal meteorological data, and historical abnormal monitoring data, as well as the historical normal power data, historical normal meteorological data, and historical normal monitoring data to obtain a pre-trained anomaly detection model.

[0093] The server compares the processed power data, processed meteorological data and processed monitoring data with the abnormal power data threshold, abnormal meteorological data threshold and abnormal monitoring data threshold, respectively, and sets the data exceeding the preset data threshold as candidate abnormal data. The server performs time series analysis, pattern recognition and statistical analysis on the candidate abnormal data to obtain the abnormal data features corresponding to the candidate abnormal data, so as to more accurately and detailedly reflect the characteristics of the candidate abnormal data in terms of time series, data regularity and statistics through the data features. The server inputs the candidate abnormal data and the abnormal data features corresponding to the candidate abnormal data into the pre-trained anomaly detection model, so as to further distinguish the abnormal data through the pre-trained anomaly detection model, and finally output the anomaly detection result.

[0094] In this embodiment, candidate abnormal data exceeding a preset data threshold are first roughly screened out from processed power data, processed meteorological data, and processed monitoring data; then, through a pre-trained abnormality detection model, potential abnormal data are further accurately determined based on the candidate abnormal data and abnormal data features corresponding to the candidate abnormal data, thereby improving the efficiency of abnormality detection while also improving the accuracy of abnormality detection.

[0095] In one embodiment, the above step S203 performs abnormal event classification processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result, which specifically includes the following contents: the processed power data, the processed meteorological data and the processed monitoring data are input into a pre-trained event classification model to obtain the abnormal event category of the abnormal detection result; based on the knowledge base of the power grid scenario, the abnormal detection result is evaluated to obtain the handling priority of the abnormal detection result; the abnormal event category and the handling priority are used as the abnormal event information.

[0096] Among them, the event classification model can be constructed through unsupervised clustering algorithms, such as K-means (K-means clustering algorithm), DBSCAN (density-based clustering algorithm) and other clustering algorithms; the event classification model can also be constructed through supervised machine learning and deep learning models, such as support vector machines, random forests, deep neural networks and other models.

[0097] Specifically, the server can input the processed power data, processed meteorological data and processed monitoring data into the pre-trained event classification model, or only input the candidate abnormal data in the processed power data, processed meteorological data and processed monitoring data into the pre-trained event classification model to improve the data processing efficiency of the pre-trained event classification model; the pre-trained event classification model performs abnormal event classification processing on the input data and outputs the abnormal event category of the abnormal detection result. The server can also perform abnormal evaluation on the abnormal detection results based on the knowledge base and expert library of the power grid scenario to obtain the handling priority, abnormal severity and abnormal event nature of the abnormal detection results; finally, the abnormal event information is formed by integrating various information such as abnormal event category, handling priority, abnormal severity and abnormal event nature.

[0098] In actual applications, human intervention can also be used to reconfirm abnormal events and eliminate false alarms. The server can also automatically record all detected events, including event type, timestamp, location, preliminary assessment results, etc. The server can also generate corresponding alerts based on the severity and urgency of the event to notify the emergency response team and relevant stakeholders.

[0099] In this embodiment, by analyzing the abnormal event information such as the abnormal event category and handling priority, the urgency and resource requirements of the abnormal event can be more accurately and comprehensively reflected, so as to generate more reasonable and accurate target emergency handling information for the abnormal event and improve the emergency handling effect of the power grid scenario.

[0100] In one embodiment, the above step S201 performs data preprocessing on the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data, specifically including the following contents: performing data cleaning processing on the current power data, the current meteorological data, and the current monitoring data to obtain cleaned power data, cleaned meteorological data, and cleaned monitoring data; performing feature engineering processing on the cleaned power data, cleaned meteorological data, and cleaned monitoring data to obtain processed power data, processed meteorological data, and processed monitoring data.

[0101] Specifically, in addition to collecting current power data, current meteorological data, and current monitoring data in real time, the server can also collect data from multiple channels, such as sensors, Supervisory Control And Data Acquisition (SCADA), smart meters, video surveillance, drone inspections, and other equipment in the power system, as well as external systems such as weather forecasts, social media information, and public safety reports. For ease of reference, these real-time collected data are collectively referred to as current data. The server cleans the current data to remove invalid data, duplicate data, and outliers in the current data to obtain cleaned current data; the cleaned data is converted into a unified format to obtain converted data for subsequent data analysis and processing. The server can select data types that are useful for model analysis from the converted data through feature engineering, such as determining data types that are useful for model analysis through time series analysis and geographic spatial analysis, and finally output the processed data.

[0102] In actual applications, an efficient data warehouse can also be established to store and manage collected data to ensure data security and accessibility. Data encryption, access control and other measures can also be implemented to protect sensitive information and ensure data security in compliance with industry standards and laws and regulations. Data integrity and consistency can also be checked regularly to ensure data availability. Real-time data updates must be ensured to reflect the latest grid status and external environmental changes.

[0103] In this embodiment, by performing data preprocessing such as data cleaning and feature engineering on the acquired current power data, current meteorological data, and current monitoring data, the quality and applicability of the data are ensured, providing reliable data support for subsequent steps.

[0104] In one embodiment, Figure 4 As shown, another emergency disposal method is provided, which is applied to Figure 1 The server in the example is used to illustrate the following steps:

[0105] Step S401, preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data.

[0106] Step S402, screen out candidate abnormal data exceeding a preset data threshold from the processed power data, processed meteorological data and processed monitoring data; input the candidate abnormal data and the abnormal data features corresponding to the candidate abnormal data into a pre-trained abnormal detection model to obtain an abnormal detection result.

[0107] Step S403, if it is detected that the abnormal detection result represents an abnormality, the processed power data, the processed meteorological data and the processed monitoring data are input into a pre-trained event classification model to obtain the abnormal event category of the abnormal detection result.

[0108] Step S404, based on the knowledge base of the power grid scenario, an abnormality assessment is performed on the abnormality detection result to obtain the handling priority of the abnormality detection result; the abnormal event category and handling priority are used as abnormal event information.

[0109] Step S405, obtaining preset emergency handling information that matches the abnormal event information and the abnormal detection result.

[0110] Step S406, using the trained emergency response scheduling model, the resource configuration information in the preset emergency response information is optimized to obtain optimized emergency response information.

[0111] Step S407 , using the trained emergency response scheduling model, performing path optimization processing on the path planning information in the optimized emergency response information to obtain target emergency response information.

[0112] Step S408, obtaining an immediate evaluation result of the target emergency handling information according to the emergency response speed, resource utilization rate, and abnormal event control speed within the first period of time after the target emergency handling information is executed in the power grid scenario.

[0113] Step S409, obtaining a long-term evaluation result of the target emergency handling information based on the power operation data and environmental data within a second time period after the target emergency handling information is executed according to the power grid scenario; the second time period is greater than the first time period.

[0114] Step S410, updating the preset emergency response information and the trained emergency response scheduling model according to the immediate evaluation results and the long-term evaluation results.

[0115] The above-mentioned emergency response method can achieve the following beneficial effects: it can capture anomalies from real-time data from multiple sources, quickly classify abnormal events and initiate corresponding target emergency response information, ensuring the efficiency of emergency response to power grid scenarios and providing guarantees for the safe operation of power grid scenarios.

[0116] In order to more clearly illustrate the emergency handling method provided by the embodiment of the present disclosure, the above emergency handling method is specifically described below with a specific embodiment. Another emergency handling method is provided, which can be applied to Figure 1 The server in the system includes the following:

[0117] (1) Data acquisition and preprocessing: Collect multiple data such as smart grid, weather station, satellite remote sensing, etc., and clean, convert and integrate them.

[0118] (2) Event identification and classification: Analyze data and extract key features, and use anomaly detection technology to identify any activities that deviate from normal patterns. If a potential event is detected, a pre-trained machine learning model is used to classify it and determine the type of event; then these events are confirmed and preliminarily evaluated in combination with the knowledge of domain experts, and finally corresponding alerts and targeted emergency response information are generated.

[0119] (3) Response strategy generation and execution monitoring: Call or generate appropriate emergency response strategies based on event characteristics, and dynamically schedule and optimize resources to ensure the most efficient allocation of manpower and materials.

[0120] (4) Response effect evaluation and learning iteration: After the emergency response is completed, a comprehensive evaluation is conducted on the immediate and long-term effects of the emergency response. Based on the evaluation results, the machine learning model and emergency response plan are updated, and the knowledge graph in the field of emergency response is constructed or updated to enhance the support capabilities of the machine learning model.

[0121] In this embodiment, comprehensive intelligent management of power emergency response is achieved by integrating a series of modules such as real-time data collection, anomaly detection and early warning, intelligent plan matching, dynamic tracking of execution process, intelligent resource scheduling, post-analysis and model optimization. Machine learning and deep learning algorithms are used to analyze multi-source heterogeneous data, so as to quickly and accurately identify power grid anomalies, dynamically adjust emergency strategies, optimize resource allocation, ensure the efficiency and accuracy of emergency response, and continuously improve system performance through continuous learning mechanisms, providing strong technical support for the safe operation of the power industry.

[0122] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0123] Based on the same inventive concept, the embodiment of the present application also provides an emergency disposal device for implementing the emergency disposal method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more emergency disposal device embodiments provided below can refer to the limitations on the emergency disposal method above, and will not be repeated here.

[0124] In one embodiment, Figure 5 As shown, an emergency handling device 500 is provided, comprising: a data acquisition module 501, an anomaly detection module 502, an event classification module 503 and an emergency handling module 504, wherein:

[0125] The data acquisition module 501 is used to preprocess the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data.

[0126] The anomaly detection module 502 is used to perform anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain anomaly detection results for the power grid scenario.

[0127] The event classification module 503 is used to perform abnormal event classification processing on the processed power data, the processed meteorological data and the processed monitoring data if the abnormal detection result indicates an abnormality, so as to obtain abnormal event information corresponding to the abnormal detection result.

[0128] The emergency handling module 504 is used to determine target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result.

[0129] In one embodiment, the emergency response module 504 is also used to obtain preset emergency response information that matches the abnormal event information and the abnormal detection results; through the trained emergency response scheduling model, the resource configuration information in the preset emergency response information is configured and optimized to obtain the optimized emergency response information; through the trained emergency response scheduling model, the path planning information in the optimized emergency response information is path optimized to obtain the target emergency response information.

[0130] In one embodiment, the emergency handling device 500 also includes a model updating module, which is used to obtain an immediate evaluation result of the target emergency handling information based on the emergency response speed, resource utilization, and abnormal event control speed within a first time period after the power grid scenario executes the target emergency handling information; obtain a long-term evaluation result of the target emergency handling information based on the power operation data and environmental data within a second time period after the power grid scenario executes the target emergency handling information; the second time period is greater than the first time period; based on the immediate evaluation result and the long-term evaluation result, the preset emergency handling information and the trained emergency handling scheduling model are updated.

[0131] In one embodiment, the anomaly detection module 502 is also used to screen out candidate anomaly data that exceeds a preset data threshold from the processed power data, the processed meteorological data, and the processed monitoring data; and input the candidate anomaly data and the anomaly data features corresponding to the candidate anomaly data into a pre-trained anomaly detection model to obtain anomaly detection results.

[0132] In one embodiment, the event classification module 503 is also used to input the processed power data, processed meteorological data and processed monitoring data into a pre-trained event classification model to obtain the abnormal event category of the abnormal detection result; based on the knowledge base of the power grid scenario, perform an abnormal evaluation on the abnormal detection result to obtain the handling priority of the abnormal detection result; and use the abnormal event category and handling priority as abnormal event information.

[0133] In one embodiment, the data acquisition module 501 is also used to perform data cleaning processing on the current power data, the current meteorological data and the current monitoring data to obtain cleaned power data, cleaned meteorological data and cleaned monitoring data; perform feature engineering processing on the cleaned power data, cleaned meteorological data and cleaned monitoring data to obtain processed power data, processed meteorological data and processed monitoring data.

[0134] Each module in the above emergency response device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0135] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as current power data and current meteorological data of meteorological scenes. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an emergency disposal method is implemented.

[0136] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0137] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0138] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0139] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0140] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile 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), magnetoresistive 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0141] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 specification.

[0142] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An emergency response method, characterized in that: The method comprises: Preprocessing the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data; Performing anomaly detection processing on the processed power data, the processed meteorological data, and the processed monitoring data to obtain an anomaly detection result for the power grid scenario; If it is detected that the abnormal detection result represents an abnormality, abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result; According to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario is determined.

2. The method according to claim 1, characterized in that: The determining, according to the abnormal event information and the abnormal detection result, target emergency handling information of the power grid scenario includes: Acquire preset emergency handling information that matches the abnormal event information and the abnormal detection result; By using the trained emergency response scheduling model, the resource configuration information in the preset emergency response information is optimized to obtain optimized emergency response information; The trained emergency response scheduling model is used to perform path optimization processing on the path planning information in the optimized emergency response information to obtain the target emergency response information.

3. The method according to claim 2, characterized in that After determining the target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result, the method further includes: Obtaining an immediate evaluation result of the target emergency handling information according to the emergency response speed, resource utilization rate, and abnormal event control speed within the first period of time after the target emergency handling information is executed in the power grid scenario; Obtaining a long-term evaluation result of the target emergency disposal information according to power operation data and environmental data within a second time period after executing the target emergency disposal information according to the power grid scenario; the second time period is greater than the first time period; The preset emergency response information and the trained emergency response scheduling model are updated according to the immediate evaluation result and the long-term evaluation result.

4. The method according to claim 1, characterized in that: The performing anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain an anomaly detection result for the power grid scenario includes: Screening out candidate abnormal data exceeding a preset data threshold from the processed power data, the processed meteorological data and the processed monitoring data; The candidate abnormal data and the abnormal data features corresponding to the candidate abnormal data are input into a pre-trained abnormality detection model to obtain the abnormality detection result.

5. The method according to claim 1, characterized in that The abnormal event classification processing is performed on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result, including: Inputting the processed power data, the processed meteorological data and the processed monitoring data into a pre-trained event classification model to obtain the abnormal event category of the abnormal detection result; Based on the knowledge base of the power grid scenario, performing anomaly evaluation on the anomaly detection result to obtain a handling priority of the anomaly detection result; The abnormal event category and the handling priority are used as the abnormal event information.

6. The method according to claim 1, characterized in that The data preprocessing of the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data includes: Performing data cleaning on the current power data, the current meteorological data, and the current monitoring data to obtain cleaned power data, cleaned meteorological data, and cleaned monitoring data; Feature engineering processing is performed on the cleaned power data, the cleaned meteorological data and the cleaned monitoring data to obtain the processed power data, the processed meteorological data and the processed monitoring data.

7. An emergency disposal device, characterized in that: The device comprises: A data acquisition module is used to pre-process the current power data of the power grid scenario, the current meteorological data of the meteorological scenario, and the current monitoring data of satellite remote sensing associated with the power grid scenario to obtain processed power data, processed meteorological data, and processed monitoring data; An anomaly detection module, used to perform anomaly detection processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain an anomaly detection result for the power grid scenario; An event classification module, configured to perform abnormal event classification processing on the processed power data, the processed meteorological data and the processed monitoring data to obtain abnormal event information corresponding to the abnormal detection result if the abnormal detection result indicates an abnormality; The emergency handling module is used to determine the target emergency handling information of the power grid scenario according to the abnormal event information and the abnormal detection result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Citation Information

Patent Citations

  • Method for establishing resources optimal configuration model for power distribution network emergency recovery

    CN111125887A

  • Centralized control station equipment monitoring system based on intelligent event processing and control method

    CN113409162A

  • Power grid fault early warning method and system under extreme weather

    CN116821592A