Power grid distribution early warning method, system, equipment and medium in extreme weather

Abstract

The invention discloses a power grid distribution network early warning method, system and device in extreme weather and a medium. The method comprises the following steps: acquiring extreme weather parameters and distribution network device operation data; carrying out data fusion processing on the extreme weather parameters and the operation data of the distribution network equipment, and constructing an association feature library of the extreme weather and the distribution network faults; constructing a distribution network risk conduction model through the association feature library, and generating a distribution network fault risk grade evaluation result; and the risk level assessment result is transmitted through an emergency communication network, and fault early warning information and an emergency disposal scheme are generated according to the risk level assessment result. Through cooperation of multi-source data fusion, multi-level risk identification, intelligent communication and a dynamic decision technology, the active prevention and control capability of the power grid distribution network in extreme weather is improved, deep correlation analysis of meteorology and distribution network states is realized through multi-source data integration, and potential risks caused by extreme weather are accurately identified.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid distribution network early warning, and in particular relates to a power grid distribution network early warning method, system, device and medium under extreme weather. BACKGROUND

[0002] With global climate change, extreme weather such as ice and snow, strong winds, and heavy rain occurs frequently, and its high destructive nature poses a serious challenge to the power grid distribution network system. According to statistics, the number of power system failures caused by extreme weather has increased in recent years, and the distribution network has become a disaster area due to the exposure of equipment outdoors. Disasters cause chain risks through multiple mechanisms, and traditional prevention and control methods are difficult to cope with. Traditional distribution network risk assessment is based on deterministic failure assumptions, and there are core defects such as lack of multi-source data collaboration, shallow risk transmission analysis, insufficient emergency communication resilience, and low level of decision-making intelligence: meteorological and distribution network data are independent, and there is a lack of dynamic correlation modeling; it is difficult to timely warn chain risks by staying at the device level failure identification; it is prone to interruption in disaster due to reliance on centralized communication networks; and emergency plans rely on manual work and lack of intelligent reasoning. Although existing technologies attempt to improve, they are limited by the depth of data fusion and the level of equipment intelligence, and the prevention and control effect is limited. With the development of new power systems, the complexity of distribution network structure has increased, and the traditional "passive defense" mode needs to be upgraded. Therefore, it is urgent to build an intelligent early warning system that integrates multi-source data sensing, multi-level risk reasoning, ad hoc communication support, and dynamic decision support to realize the whole-process management and control of distribution network risks under extreme weather, fill the gaps in existing technologies, and provide key support for power grid resilience and climate change response. It is of great significance to ensure power safety and low-carbon transformation. SUMMARY

[0003] In view of the above existing problems, the present application is proposed.

[0004] Therefore, the present application provides a power grid distribution network early warning method, system, device and medium under extreme weather to solve the problems of independent meteorological and distribution network data and lack of dynamic correlation modeling.

[0005] To solve the above technical problems, the present application provides the following technical solutions:

[0006] In a first aspect, the present application provides a power grid distribution network early warning method under extreme weather, comprising the following steps:

[0007] Obtain extreme weather parameters and distribution network equipment operation data;

[0008] Perform data fusion processing on the extreme weather parameters and distribution network equipment operation data to construct an associated feature library of extreme weather and distribution network failure;

[0009] A power distribution network risk transmission model is constructed based on the associated feature library to generate a power distribution network fault risk level evaluation result.

[0010] The risk level evaluation result is transmitted through an emergency communication network, and a fault early warning information and an emergency disposal scheme are generated according to the risk level evaluation result.

[0011] As a preferred scheme of the power grid power distribution network early warning method under extreme weather, the step of obtaining the extreme weather parameters and the power distribution network equipment operation data comprises:

[0012] The spatial distribution and dynamic evolution data of the extreme weather parameters are obtained through meteorological monitoring, and the output is extreme weather parameters.

[0013] The power distribution network equipment operation parameters and environmental data are collected through power distribution network sensing, and the output is power distribution network equipment operation data.

[0014] The beneficial effect of the preferred technical scheme is that through dual data collection of meteorological monitoring and power distribution network sensing, all-round monitoring of extreme weather parameters and equipment operation state is realized, ensuring the completeness and timeliness of data acquisition.

[0015] As a preferred scheme of the power grid power distribution network early warning method under extreme weather, the step of data fusion processing comprises:

[0016] The extreme weather parameters and the power distribution network equipment operation data are spatio-temporally aligned and noise filtered to obtain processed data.

[0017] Key features of the influence of extreme weather on power distribution network equipment are extracted from the processed data to construct the associated feature library.

[0018] The beneficial effect of the preferred technical scheme is that through spatio-temporal alignment and noise filtering processing, the time deviation and interference information between different data sources are eliminated, and the data quality is improved.

[0019] As a preferred scheme of the power grid power distribution network early warning method under extreme weather, the step of constructing the power distribution network risk transmission model comprises:

[0020] A power distribution network risk transmission knowledge graph is constructed through knowledge graph technology.

[0021] According to the power distribution network risk transmission knowledge graph and the associated feature library, a multi-level risk identification algorithm is used to analyze the risk caused by extreme weather to generate the power distribution network fault risk level evaluation result.

[0022] The beneficial effects of the preferred technical solution are that the knowledge graph technology realizes the structured expression of the distribution network risk transmission relationship, and the multi-level risk identification algorithm can deeply mine the risk transmission path and accurately identify potential fault points.

[0023] As a preferred scheme of the power grid distribution network early warning method under extreme weather, the establishment and transmission steps of the emergency communication network include:

[0024] A wireless ad hoc network technology is used to establish a centerless emergency communication network.

[0025] The distribution network fault risk level evaluation results are data encapsulated and routed.

[0026] The distribution network fault risk level evaluation results and control instructions are bidirectionally transmitted through the emergency communication network.

[0027] The transmission state of the emergency communication network is monitored.

[0028] The beneficial effects of the preferred technical solution are that the wireless ad hoc network technology ensures the autonomous networking and fault self-healing capability of the communication network under extreme weather, the data encapsulation and routing optimization transmission efficiency, the bidirectional transmission mechanism realizes information feedback and remote control, the transmission state monitoring guarantees the communication quality, and the overall reliability of the emergency communication is improved.

[0029] As a preferred scheme of the power grid distribution network early warning method under extreme weather, the step of generating fault warning information and emergency disposal scheme according to the risk level evaluation results includes:

[0030] According to the distribution network fault risk level evaluation results, the fault warning information and emergency disposal scheme are generated in combination with the power grid emergency plan knowledge graph.

[0031] The fault warning information and emergency disposal scheme are displayed through a visual interface.

[0032] The beneficial effects of the preferred technical solution are that the intelligent generation mechanism combined with the emergency plan knowledge graph can quickly output targeted warning information and disposal scheme, the visual interface provides intuitive decision support, and the emergency response speed and disposal efficiency are improved.

[0033] As a preferred scheme of the power grid distribution network early warning method under extreme weather, the construction and application steps of the power grid emergency plan knowledge graph include:

[0034] A power grid emergency plan knowledge graph containing device types, fault modes, and disposal measures is established.

[0035] According to the matching retrieval result in the power grid emergency plan knowledge graph according to the power distribution network fault risk level evaluation result;

[0036] The matching result is used for automatically generating fault early warning information of a hierarchical response, including risk level identification, impact range prediction, and early warning timeliness.

[0037] According to the fault type and severity, a corresponding emergency disposal scheme is extracted from the power grid emergency plan knowledge graph, including personnel scheduling, material allocation, and operation process.

[0038] The preferred technical scheme has the beneficial effects that the multi-dimensional emergency plan knowledge graph covers the complete mapping relationship of equipment-fault-disposal, the intelligent matching retrieval realizes personalized scheme recommendation, and the hierarchical response mechanism ensures the timeliness and accuracy of the early warning.

[0039] In a second aspect, the application provides a power grid distribution network early warning system under extreme weather, which comprises a data acquisition module, a feature construction module, a risk assessment module, and an early warning disposal module.

[0040] The data acquisition module is responsible for acquiring extreme weather parameters and distribution network equipment operation data.

[0041] The feature construction module performs data fusion processing on the acquired extreme weather parameters and distribution network equipment operation data, and constructs an associated feature library of extreme weather and distribution network faults.

[0042] The risk assessment module is used for constructing a distribution network risk transmission model.

[0043] The early warning disposal module transmits the generated risk level evaluation result through an emergency communication network, generates fault early warning information and emergency disposal schemes according to the risk level evaluation result.

[0044] In a third aspect, the application provides an electronic device, which comprises:

[0045] a memory and a processor;

[0046] The memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions, so as to realize the steps of the power grid distribution network early warning method under extreme weather.

[0047] In a fourth aspect, the application provides a computer readable storage medium, which stores computer executable instructions, and the computer executable instructions are executed by a processor to realize the steps of the power grid distribution network early warning method under extreme weather.

[0048] Compared with the prior art, the application has the beneficial effects that:

[0049] Through the synergy of multi-source data fusion, multi-level risk identification, intelligent communication and dynamic decision technology, the active prevention and control capability of the power grid distribution network under extreme weather is improved: multi-source data integration realizes in-depth correlation analysis of weather and distribution network state, accurately identifies potential risks caused by extreme weather; multi-level risk transmission model can early warning disaster chain evolution path, effectively avoid single fault upgrade to large area accident; self-organizing network communication technology solves the interruption problem of traditional center network in disaster, ensures the real-time transmission of early warning and disposal instruction; intelligent decision support system automatically generates emergency plan and provides on-site guidance, greatly shortens the repair response and fault repair time; the whole process data closed loop management continuously optimizes the adaptability of the system to extreme weather, forms intelligent evolution ability, realizes the change from passive to active of the risk prevention and control of distribution network under extreme weather, enhances the power grid disaster prevention and reduction ability and power supply reliability, provides key technical support for guaranteeing people's livelihood electricity and new type power system resilience. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0051] Figure 1 The whole flowchart of the power grid distribution network early warning method under extreme weather described by an embodiment of the present application.

[0052] Figure 2 The emergency communication network structure diagram of the power grid distribution network early warning method under extreme weather described by an embodiment of the present application.

[0053] Figure 3 The distribution network risk transmission knowledge graph of the power grid distribution network early warning method under extreme weather described by an embodiment of the present application. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific embodiments of the present application will be described in detail below with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the protection scope of the present application.

[0055] Embodiment 1, refer to Figure 1 , for an embodiment of the present application, a power grid distribution network early warning method under extreme weather is provided, which comprises the following steps S1-S4:

[0056] S1, acquire extreme weather parameters and distribution network equipment operation data;

[0057] S2, data fusion processing is carried out on the extreme weather parameters and the distribution network equipment operation data, and an associated feature library of extreme weather and distribution network fault is constructed;

[0058] S3, a distribution network risk transmission model is constructed through the associated feature library, and a distribution network fault risk level evaluation result is generated;

[0059] S4, the risk level evaluation result is transmitted through an emergency communication network, and a fault early warning information and an emergency disposal scheme are generated according to the risk level evaluation result.

[0060] It should be noted that, as an important part of the power system, the distribution network faces serious security threats under extreme weather conditions, such as typhoon, lightning, snow, high temperature and other adverse weather environments. Extreme weather can cause problems such as reduced insulation of distribution network lines, overheating of equipment, increased mechanical stress, etc., which increases the probability of distribution network failure and seriously affects power supply reliability. Traditional distribution network monitoring methods mainly rely on periodic inspection and post-fault processing, lack active early warning capability for extreme weather impact, and often discover problems after failure occurs, which cannot achieve preventive maintenance. At the same time, due to the complexity and unpredictability of extreme weather, existing risk assessment methods are difficult to accurately quantify the impact of weather factors on distribution network equipment and to establish an effective emergency response mechanism. Therefore, it is of great significance to establish a complete distribution network early warning system under extreme weather conditions to ensure the safe operation of the power grid.

[0061] Therefore, in view of the above monitoring and early warning and risk assessment problems, through steps S1-S4, a comprehensive analysis model integrating meteorological data and equipment operation data is constructed to realize accurate identification and quantitative evaluation of distribution network risk under extreme weather conditions; a risk transmission model based on knowledge graph is established to dynamically analyze the influence path of extreme weather on distribution network equipment and realize early warning of potential fault risk; at the same time, based on the emergency communication network and the intelligent decision support system, the rapid transmission of early warning information and the automatic generation of emergency disposal scheme are realized, which improves the emergency response capability and fault disposal efficiency of the distribution network under extreme weather conditions.

[0062] Embodiment 2, refer to Figures 1 to 3 For an embodiment of the present application, based on the above embodiment, a power distribution network early warning method under extreme weather conditions is provided.

[0063] In the present application, in step S1, the step of acquiring extreme weather parameters and distribution network equipment operation data includes A1-A2:

[0064] A1, acquire the spatial distribution and dynamic evolution data of the extreme weather parameters through meteorological monitoring, and output the extreme weather parameters;

[0065] A2, collecting power distribution equipment operation parameters and environmental data through network sensing, and outputting power distribution equipment operation data.

[0066] Specifically, in step A1, meteorological monitoring obtains extreme weather parameters through multi-source data fusion, including: obtaining regional temperature and humidity, wind speed, precipitation and other macro weather parameters by using polar orbit meteorological satellites, with a resolution of ≤5km 2 , an update frequency of ≥1 time per hour; monitoring local micro-meteorological characteristics using Doppler radar, with an accuracy of ±3dBZ and a refresh rate of ≥1 time per minute; collecting real-time wind speed, rainfall, icing thickness and other parameters through ground meteorological stations, with a data refresh rate of 5 minutes / time.

[0067] Specifically, in step A2, network sensing collects equipment operation data through intelligent sensing devices, including: collecting line load, equipment temperature, voltage and current operation parameters through intelligent sensors deployed at key nodes of the network; using AI edge recognition terminals to monitor real-time environmental data such as tower inclination angle, conductor icing thickness, and insulator contamination degree; using unmanned aerial vehicle inspection systems to perform laser radar scanning on high-risk lines to identify vegetation hazards, equipment defects and other micro abnormalities, with a daily inspection frequency of 1 time.

[0068] It should be noted that multi-source meteorological data is fused through a space-time calibration algorithm to eliminate time deviations and spatial offsets between different data sources; network sensing data is preprocessed through edge computing to achieve data compression and outlier filtering, providing high-quality basic data for subsequent risk analysis.

[0069] In an alternative embodiment, the extreme weather parameters obtained in step S1 can also be obtained through a meteorological numerical prediction model, combined with historical meteorological data and real-time observation data, to predict weather trends for the next 6-72 hours, providing forward-looking meteorological information for power distribution network warning.

[0070] In another alternative embodiment, the collection of power distribution equipment operation data in step S1 can also be achieved through a power distribution SCADA system interface to obtain real-time operation status and protection device action information of substations and switch stations, realizing unified collection and monitoring of the entire network equipment operation status.

[0071] In the embodiments of the present application, in step S2, the data fusion processing step includes B1-B2:

[0072] B1, performing space-time alignment and noise filtering on the extreme weather parameters and power distribution equipment operation data to obtain processed data;

[0073] B1, extracting key features of the influence of extreme weather on power distribution equipment from the processed data to construct an associated feature library.

[0074] Specifically, in step B1, the specific implementation of spatio-temporal alignment and noise filtering includes:

[0075] The spatio-temporal alignment process calibrates the meteorological and distribution network data from different sources in space and time through the Kalman filter algorithm, eliminates the inconsistency of the data caused by device clock deviation and geographical location difference, establishes a unified spatio-temporal coordinate system to ensure that the data of different monitoring nodes can be accurately mapped to the same spatio-temporal reference, and uses an interpolation algorithm to resample the data with inconsistent time intervals to achieve time synchronization of the data.

[0076] The noise filtering adopts a multi-level filtering strategy: abnormal data points beyond the normal range are identified and removed through statistical methods; the median filtering technique is used for vibration data to eliminate random pulse interference during device operation; wavelet transform is used to denoise the meteorological radar data to separate useful signals from environmental noise; and moving average filtering is used to smooth the fluctuations of slowly varying parameters such as temperature and humidity.

[0077] Specifically, in step B2, the key feature extraction and associated feature library construction include:

[0078] The extreme weather feature extraction quantifies the destructive intensity of extreme weather by analyzing dynamic features such as wind speed change gradient, rainfall intensity cumulative effect, and ice thickness growth trend; constructs a multi-dimensional weather feature vector combining temperature and humidity coupling effect, pressure change rate, and other composite meteorological parameters; and extracts periodic and sudden features of weather changes using frequency domain analysis techniques.

[0079] The distribution network device impact feature extraction identifies the response mode of the device under extreme weather based on device load change, temperature rise effect, and mechanical stress change; establishes the mapping relationship between weather parameters and device failures through correlation analysis to identify high-risk weather-device combinations; extracts key feature combinations affecting the safety of distribution networks using principal component analysis to remove redundant information; establishes device failure feature templates under typical extreme weather conditions based on historical failure cases; and uses clustering algorithms to group similar weather-failure patterns to form a structured associated feature knowledge base.

[0080] It should be noted that this feature extraction process combines the dual advantages of physical mechanism and data statistics, considering both the direct physical impact mechanism of extreme weather on distribution network devices and the potential association patterns discovered through big data analysis, providing a scientific and reliable feature basis for subsequent risk identification.

[0081] In an optional embodiment, the data fusion processing in step S2 can also use an autoencoder in deep learning for feature extraction, automatically discover the implicit feature patterns in weather and equipment data through unsupervised learning, and improve the intelligent level and accuracy of feature extraction.

[0082] In another optional embodiment, the construction of the associated feature library in step S2 can also combine expert knowledge and experience rules, combine the fault diagnosis experience of field experts with data-driven methods, construct a feature association network containing causal relationships, and enhance the explainability and engineering practicability of the feature library. The indicators such as frequency spectrum analysis, insulation performance change, and protection device action frequency are used to evaluate the deterioration degree of the health state of the equipment; and the static attributes such as equipment material, installation environment, and operation life are used to construct a device vulnerability feature library.

[0083] In the embodiments of the present application, in step S3, the step of constructing the distribution network risk conduction model includes C1-C2:

[0084] C1, constructing a distribution network risk conduction knowledge graph through knowledge graph technology;

[0085] C2, according to the distribution network risk conduction knowledge graph and the associated feature library, using a multi-level risk identification algorithm to analyze the risk caused by extreme weather, and generating a distribution network fault risk level evaluation result.

[0086] Specifically, in step C1, the construction of the distribution network risk conduction knowledge graph includes: entity extraction and modeling, identifying key entities in the distribution network system, including but not limited to weather type entities, device type entities, fault mode entities, and influence area entities, and establishing an entity attribute library; defining detailed attributes for each type of entity, such as device entity including model, material, installation location, operation life, and weather entity including intensity level, duration, and influence range.

[0087] Relationship extraction and modeling based on historical fault data and expert knowledge, identifying causal relationships, influence relationships, and conduction relationships between entities; establishing a ternary relationship model of “weather conditions-equipment types-fault probabilities”, quantifying the influence degree of different weather conditions on various types of equipment; constructing a conduction relationship chain of “device fault-network topology-chain reaction”, describing the path of single-point fault to systemic risk diffusion.

[0088] Knowledge fusion and reasoning integrate multi-source knowledge, including device manufacturer technical data, operation and maintenance experience knowledge, and meteorological disaster mechanism; using ontology mapping technology to solve the concept conflict and semantic difference of different knowledge sources; establishing a reasoning rule library to support rule-based automatic reasoning, such as “when the wind speed exceeds the wind resistance level of the equipment and the duration exceeds the threshold, the equipment collapse risk increases”.

[0089] Specifically, in step C2, the multi-level risk identification algorithm and risk level assessment include: regional level risk identification identifies the impact range and intensity distribution of extreme weather based on meteorological forecast data and distribution of distribution network; combined with the topology of distribution network, the exposure risk of important substations and main lines in the region is analyzed; the spatial overlay analysis is used to calculate the comprehensive risk index of different regions and identify high-risk areas.

[0090] Line level risk identification analyzes the coupling effect of tower material, line diameter specification, geographical environment and extreme weather for specific lines; based on fault tree analysis method, the risk transmission chain of "extreme weather-equipment failure-line interruption" is constructed; through Monte Carlo simulation, the fault probability distribution of lines under different weather intensity is quantified.

[0091] User level risk identification identifies the power supply path and backup power supply configuration of important users, and evaluates the power supply reliability of the users under extreme weather; analyzes the load characteristics and power outage sensitivity of the users, and determines the key users to be prioritized; a user influence evaluation model is established to quantify the economic and social impact of power outage on different types of users.

[0092] Risk level assessment generates comprehensive risk analysis results of regional level, line level and user level, and establishes a multi-dimensional risk assessment matrix; the weights of different risk factors are determined by using analytic hierarchy process, and the comprehensive risk score is calculated; according to the risk score threshold, the risk level is divided into blue, yellow, orange and red four levels, corresponding to low risk, medium risk, high risk and extremely high risk state.

[0093] It should be noted that the risk transmission model realizes the whole chain analysis from single equipment failure to systematic risk through the structured representation of knowledge graph, and the multi-level risk identification algorithm can accurately locate the risk source and transmission path, providing a scientific basis for formulating targeted prevention and control measures.

[0094] In an optional embodiment, the distribution network risk transmission knowledge graph constructed in step S3 can also use graph neural network technology to automatically discover complex risk transmission patterns through deep learning, improving the expression ability and reasoning accuracy of the knowledge graph.

[0095] In another optional embodiment, the multi-level risk identification in step S3 can also combine power system flow calculation to dynamically analyze the load transfer and power grid operating state changes caused by extreme weather, achieving more accurate risk quantification assessment.

[0096] In the embodiments of the present application, in step S4, the establishment and transmission steps of the emergency communication network include D1-D4:

[0097] D1, a wireless ad hoc network technology is used to establish a centerless emergency communication network;

[0098] D2, data encapsulation and routing selection of the distribution network fault risk level assessment results;

[0099] D3, two-way transmission of the distribution network fault risk level assessment results and control instructions through the emergency communication network;

[0100] D4, monitoring the transmission state of the emergency communication network.

[0101] Specifically, in step D1, the establishment of the centerless emergency communication network includes: network topology construction adopts a distributed Adhoc self-organizing network architecture, each communication node has independent networking capability and does not need to rely on fixed base stations; vehicle-mounted relay nodes and portable communication terminals are deployed to form a multi-hop transmission network supporting dynamic topology changes; MIMO-OFDM physical layer technology is used to adopt multi-transmit and multi-receive antenna configuration to ensure communication quality in non-line-of-sight environments.

[0102] The network adaptive mechanism automatically identifies available communication nodes through a neighbor discovery protocol and establishes adjacency relationships; a distributed routing algorithm is used, each node maintains local topology information, and supports multi-path concurrent transmission; it has network self-healing capability, and when part of the nodes fail, it automatically reconstructs the communication path to ensure network connectivity.

[0103] Spectrum management and anti-interference use cognitive radio technology to dynamically perceive spectrum usage and intelligently select the optimal operating frequency band; integrate Beidou short message communication modules to provide backup communication means in extreme cases; use spread spectrum communication and frequency hopping technology to enhance the anti-interference and anti-interception capabilities of signals.

[0104] Specifically, in step D2, the implementation of data encapsulation and routing selection includes: data encapsulation processing structures the distribution network fault risk level assessment results, including risk level, impact range, timestamp, priority and other key information; using data compression algorithms to reduce transmission bandwidth occupancy, setting different compression strategies for different types of data; adding digital signature and encryption processing to ensure the security and integrity of data transmission.

[0105] The routing selection strategy selects the optimal transmission path based on network topology and link quality information using a multi-path routing algorithm; a load balancing mechanism is introduced to avoid transmission delays caused by overloading a single path; different routing is performed according to data priority, with emergency data being given priority to the shortest path and general data being given priority to the path with lighter load.

[0106] The service quality guarantee mechanism establishes a multi-level cache queue to process different priority data; adaptive modulation and coding technology is used to dynamically adjust the modulation method and coding rate according to channel quality; end-to-end reliable transmission is achieved to ensure data integrity through an acknowledgement and retransmission mechanism.

[0107] Specifically, in step D3, the implementation of the bidirectional transmission mechanism includes: the uplink transmission management front-end monitoring device uploads risk assessment results, field state information, device operation data, etc. to the main station through the emergency communication network; an event-driven transmission strategy is adopted, and when a risk level change or an abnormal event is detected, it is immediately reported; a data priority queue is established to ensure that critical information is transmitted first.

[0108] The downlink instruction distribution main station issues control instructions, emergency plans, resource scheduling schemes, etc. to the field devices through the emergency communication network; a transmission mode combining broadcasting and unicasting is adopted, and the appropriate transmission mode is selected according to the nature of the instructions; an instruction confirmation mechanism is established to ensure that the field devices correctly receive and execute the instructions.

[0109] Transmission synchronization coordination establishes a unified time synchronization mechanism to ensure the time consistency of uplink and downlink data; flow control technology is used to avoid bidirectional transmission conflicts and network congestion; real-time feedback of transmission status is realized to facilitate timely detection and handling of transmission abnormalities.

[0110] Specifically, in step D4, the implementation of transmission status monitoring includes: network performance monitoring real-time monitors key indicators such as signal strength, packet loss rate, and transmission delay of each communication node; a network health evaluation model is established to comprehensively evaluate the overall operation status of the network; visual technology is used to display network topology and performance status to facilitate operators to quickly locate problems.

[0111] Link quality assessment periodically tests the performance parameters such as bandwidth, delay, and jitter of each communication link; a link quality database is established to record historical performance data and support trend analysis; when the link quality is detected to be declining, path reselection and network reconstruction are automatically triggered.

[0112] Fault detection and recovery uses a heartbeat detection mechanism to detect node failures and link interruptions in a timely manner; a fault alarm system is established to notify operators immediately when the network is abnormal; it has the ability of fault self-healing, automatically starting the standby communication path to minimize communication interruption time.

[0113] It should be noted that the emergency communication network is designed to fully consider the harsh communication environment in extreme weather, and through a decentralized architecture and multiple redundancy mechanisms, it can ensure reliable communication capabilities even in the case of damaged infrastructure, providing solid communication support for distribution network emergency command.

[0114] In an alternative embodiment, the emergency communication network in step S4 can also integrate satellite communication technology, which can maintain the transmission of critical information through satellite links in extreme cases where ground communication is completely interrupted, further improving the reliability of the communication system.

[0115] In another alternative embodiment, the transmission state monitoring in step S4 can also use artificial intelligence technology for network performance prediction, by analyzing historical monitoring data to identify potential network failure risks in advance, to achieve preventive maintenance and optimization.

[0116] In the embodiments of the present application, in step S4, the step of generating failure warning information and emergency disposal scheme according to the risk level evaluation result includes E1-E2:

[0117] E1, according to the risk level evaluation result of the distribution network fault, combined with the power grid emergency plan knowledge graph to generate the fault warning information and the emergency disposal scheme;

[0118] Among them, the construction and application steps of the power grid emergency plan knowledge graph include E1.1-E1.4:

[0119] E1.1, establish a power grid emergency plan knowledge graph containing device type, fault mode and disposal measures;

[0120] The establishment of the power grid emergency plan knowledge graph includes: the device type ontology construction classifies the distribution network equipment according to the function and structure characteristics, establishes the device entities such as transformers, switch devices, lines and towers; define detailed attribute information for each type of equipment, including technical parameters, installation environment, maintenance history, vulnerability characteristics, etc.; establish the hierarchical relationship and association relationship between devices, such as the hierarchical structure of transformer substation containing transformer, switch and other devices.

[0121] Fault mode knowledge modeling is based on historical fault data and expert experience to identify typical fault modes of various devices under extreme weather conditions; establish the association relationship of fault cause, fault phenomenon and fault consequence, such as the causal chain of ice covering leading to conductor fracture; construct a fault evolution path model to describe the process of single fault developing into cascading failure.

[0122] The disposal measures are standardized and arranged, and the mature emergency disposal experience and standard operation procedures are structured; establish the mapping relationship between disposal measures and fault types, including emergency repair, load transfer, device isolation and other operations; define detailed information of disposal measures such as execution condition, operation steps, required resources and expected effect.

[0123] E1.2, according to the risk level evaluation result of the distribution network fault, matching retrieval is carried out in the power grid emergency plan knowledge graph;

[0124] The implementation of the matching retrieval mechanism includes: the semantic matching algorithm uses the semantic similarity calculation based on the vector space model to convert the risk evaluation result into a feature vector; use word embedding technology to process text information such as device name and fault description to improve matching accuracy; establish a multi-dimensional matching strategy, considering multiple factors such as device type, weather condition and risk level.

[0125] The knowledge reasoning mechanism is based on ontology reasoning technology to deduce potential failure modes and impact range from known risk information; a rule-based reasoning engine is used to make logical inferences according to a predefined rule set; fuzzy matching and approximate reasoning are supported to handle incomplete matching cases.

[0126] The retrieval optimization strategy establishes an indexing mechanism to improve the retrieval efficiency of large-scale knowledge bases; a caching technique is used to cache and store the results of frequent queries; an incremental update mechanism is implemented to automatically update the index and cache when the knowledge base is updated.

[0127] E1.3, automatically generate hierarchical response fault warning information based on matching results, including risk level identification, impact range prediction and warning timeliness;

[0128] The generation of hierarchical response fault warning information includes: risk level identification generation automatically determines the warning level according to the risk assessment results, uses color coding and numerical level double identification; combined with historical statistical data, calculates the risk occurrence probability and the possible loss degree; establish a dynamic adjustment mechanism, real-time update risk level according to weather changes and equipment state.

[0129] Impact range prediction analysis is based on power grid topology and power flow distribution to calculate the range of users and load capacity that may be affected by the fault; network analysis algorithm is used to identify key nodes and weak links; considering the standby power and transfer capacity, the actual power outage impact range is evaluated.

[0130] The determination of warning timeliness determines the warning release time according to the development trend of extreme weather and the response time of equipment; a phased warning mechanism is established, including warning preparation, warning release, warning escalation, and warning removal; set the automatic trigger condition, when the risk reaches the threshold, immediately release the warning.

[0131] E1.4, according to the fault type and severity, extract the corresponding emergency disposal scheme from the power grid emergency plan knowledge graph, including personnel dispatching, material allocation and operation process.

[0132] The extraction of emergency disposal scheme includes: personnel dispatching scheme generation is based on fault type and impact range, automatically matches the required professional skills and number of personnel; considering factors such as personnel location, skill level, and work load, optimize the personnel dispatching strategy; establish an emergency linkage mechanism to coordinate internal and external rescue forces of power enterprises.

[0133] Material allocation scheme development automatically generates a list of required materials based on fault disposal needs, including spare parts, emergency equipment, and repair tools; based on material inventory and transportation conditions, optimize the material allocation path; establish a material preposition mechanism to deploy critical materials in advance during high-risk periods.

[0134] The operation flow standardization output decomposes the complex emergency disposal process into standardized operation steps; provides detailed job instructions, including safety precautions, operation points, quality standards, etc.; establishes a process monitoring mechanism to track the disposal progress and effect.

[0135] E2, the visual interface displays fault warning information and emergency disposal scheme.

[0136] The implementation of the visual interface display includes:

[0137] The geographic information system integration uses GIS technology to display distribution of distribution network equipment and risk areas, supports multi-layer superimposed display; real-time updates equipment status and weather information, provides dynamic situation awareness; supports spatial query and analysis functions, facilitating quick positioning of problem areas.

[0138] The warning information visualization uses the form of instrument panel to display key indicators and warning state, supports multi-dimensional data display; uses heat map, contour line and other ways to intuitively display risk distribution; provides warning history record and trend analysis function.

[0139] The emergency scheme display displays the emergency disposal scheme through flowchart, timeline and other forms; supports mobile access, facilitating on-site personnel to view and execute; integrates augmented reality technology to provide intelligent guidance for on-site operation.

[0140] It should be noted that the warning information generation and disposal scheme making system realizes the structured storage and intelligent application of emergency disposal experience through knowledge graph technology, can automatically generate targeted disposal schemes according to different fault scenarios, and improves the efficiency and accuracy of emergency response.

[0141] In an alternative embodiment, the power grid emergency plan knowledge graph in step E1 can also be continuously optimized using machine learning technology, by analyzing disposal effect and feedback information, automatically updating and improving the plan content, and improving the applicability and accuracy of the knowledge graph.

[0142] In another alternative embodiment, the visual interface in step E2 can also integrate voice interaction and natural language processing technology, support voice query and instruction input, and provide more convenient human-computer interaction mode for operators in extreme environment.

[0143] In summary, through the synergy of multi-source data fusion, multi-level risk identification, intelligent communication and dynamic decision-making technology, the active prevention and control capability of the power grid distribution network under extreme weather is improved: multi-source data integration realizes in-depth correlation analysis of weather and distribution network status, accurately identifies potential risks caused by extreme weather; the multi-level risk transmission model can early warn the disaster chain evolution path, effectively avoid the single fault upgrading to large area accident; the self-organizing network communication technology solves the interruption problem of traditional center network in disaster, ensures the real-time transmission of early warning and disposal instruction; the intelligent decision support system automatically generates emergency plan and provides on-site guidance, greatly shortens the repair response and fault repair time; the whole-process data closed-loop management continuously optimizes the adaptability of the system to extreme weather, forms intelligent evolution ability, realizes the transformation of distribution network risk prevention and control from passive to active under extreme weather, enhances the power grid disaster prevention and reduction ability and power supply reliability, and provides key technical support for guaranteeing people's livelihood electricity and new type power system resilience.

[0144] In some embodiments, the above is a schematic scheme of a power grid distribution network early warning method under extreme weather. It should be noted that the technical scheme of the power grid distribution network early warning system under extreme weather belongs to the same concept as the technical scheme of the power grid distribution network early warning method under extreme weather described above. The technical scheme of the power grid distribution network early warning system under extreme weather in this embodiment is not described in detail, and can be referred to the description of the technical scheme of the power grid distribution network early warning method under extreme weather.

[0145] In some embodiments, the above is a schematic scheme of a power grid distribution network early warning method under extreme weather. It should be noted that the technical scheme of the power grid distribution network early warning system under extreme weather belongs to the same concept as the technical scheme of the power grid distribution network early warning method under extreme weather described above. The technical scheme of the power grid distribution network early warning system under extreme weather in this embodiment is not described in detail, and can be referred to the description of the technical scheme of the power grid distribution network early warning method under extreme weather.

[0146] The data acquisition module is responsible for acquiring extreme weather parameters and distribution network equipment operation data.

[0147] The feature construction module performs data fusion processing on the acquired extreme weather parameters and distribution network equipment operation data, and constructs an associated feature library of extreme weather and distribution network failure.

[0148] The risk assessment module is used to construct a distribution network risk transmission model.

[0149] The early warning and disposal module transmits the generated risk level assessment result through the emergency communication network, generates failure warning information and emergency disposal scheme according to the risk level assessment result.

[0150] In some embodiments, the above is a schematic scheme of a power grid distribution network early warning method under extreme weather. It should be noted that the technical scheme of the power grid distribution network early warning system under extreme weather belongs to the same concept as the technical scheme of the power grid distribution network early warning method under extreme weather described above. The technical scheme of the power grid distribution network early warning system under extreme weather in this embodiment is not described in detail, and can be referred to the description of the technical scheme of the power grid distribution network early warning method under extreme weather.

[0151] The embodiment also provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the power grid distribution network early warning method under extreme weather conditions.

[0152] The storage medium proposed by the embodiment belongs to the same inventive concept as the power grid distribution network early warning method under extreme weather conditions proposed by the above embodiment, and the technical details not described in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0153] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary universal hardware, and of course can also be realized by hardware. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH memory, a hard disk, or an optical disc, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.

[0154] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A power grid distribution network early warning method under extreme weather, characterized in that, The method comprises the following steps: obtaining extreme weather parameters and distribution network equipment operation data; performing data fusion processing on the extreme weather parameters and the distribution network equipment operation data to construct an associated feature library of extreme weather and distribution network faults; constructing a distribution network risk transmission model through the associated feature library to generate a distribution network fault risk level evaluation result; transmitting the risk level evaluation result through an emergency communication network and generating fault warning information and emergency disposal schemes according to the risk level evaluation result.

2. The power grid distribution network early warning method under extreme weather of claim 1, wherein, The step of obtaining the extreme weather parameters and the distribution network equipment operation data comprises: obtaining spatial distribution and dynamic evolution data of the extreme weather parameters through meteorological monitoring and outputting the extreme weather parameters; obtaining distribution network equipment operation parameters and environmental data through distribution network sensing and outputting the distribution network equipment operation data.

3. The power grid distribution network early warning method under extreme weather of claim 2, wherein, The step of data fusion processing comprises: performing time-space alignment and noise filtering on the extreme weather parameters and the distribution network equipment operation data to obtain processed data; extracting key features of the influence of extreme weather on the distribution network equipment from the processed data to construct the associated feature library.

4. The power grid distribution network early warning method under extreme weather of claim 3, wherein, The step of constructing the distribution network risk transmission model comprises: constructing a distribution network risk transmission knowledge graph through a knowledge graph technology; analyzing risks caused by extreme weather by using a multi-level risk identification algorithm according to the distribution network risk transmission knowledge graph and the associated feature library to generate the distribution network fault risk level evaluation result.

5. The method of claim 4, wherein the method further comprises: The step of establishing and transmitting the emergency communication network comprises: establishing a centerless emergency communication network by using a wireless ad hoc network technology; performing data encapsulation and routing selection on the distribution network fault risk level evaluation result; transmitting the distribution network fault risk level evaluation result and control instructions bidirectionally through the emergency communication network; monitoring the transmission state of the emergency communication network.

6. The method of claim 5, wherein the method further comprises: The step of generating fault warning information and emergency disposal schemes according to the risk level evaluation result comprises: generating the fault warning information and the emergency disposal schemes according to the distribution network fault risk level evaluation result in combination with a power grid emergency plan knowledge graph; displaying the fault warning information and the emergency disposal schemes through a visual interface.

7. The method of claim 6, wherein the method further comprises: The step of constructing and applying the power grid emergency plan knowledge graph comprises: establishing a power grid emergency plan knowledge graph containing device types, fault modes and disposal measures; performing matching retrieval in the power grid emergency plan knowledge graph according to the distribution network fault risk level evaluation result; automatically generating fault warning information of a hierarchical response including risk level identification, impact range prediction and warning timeliness based on a matching result; extracting corresponding emergency disposal schemes including personnel dispatching, material allocation and operation processes from the power grid emergency plan knowledge graph according to fault types and severity.

8. A power grid distribution network early warning system under extreme weather conditions, applying the method according to any one of claims 1-7, characterized in that, The system comprises a data acquisition module, a feature construction module, a risk evaluation module and an early warning and disposal module; the data acquisition module is responsible for obtaining extreme weather parameters and distribution network equipment operation data; the feature construction module performs data fusion processing on the obtained extreme weather parameters and distribution network equipment operation data to construct an associated feature library of extreme weather and distribution network faults; the risk evaluation module is used for constructing a distribution network risk transmission model; The early warning treatment module transmits the generated risk level evaluation result through an emergency communication network, generates fault early warning information and an emergency treatment scheme according to the risk level evaluation result. 9.An electronic device, comprising: a memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions, and the computer executable instructions, when executed by the processor, implement the steps of the power grid distribution network early warning method under extreme weather conditions according to any one of claims 1 to 7. 10.A computer readable storage medium storing computer executable instructions, and the computer executable instructions, when executed by a processor, implement the steps of the power grid distribution network early warning method under extreme weather conditions according to any one of claims 1 to 7.

Images