Large power grid and backbone optical communication system operation fault early warning method and system

Abstract

The invention relates to a large power grid and backbone optical communication system operation fault early warning method and system. The method comprises the steps that a fault data set is constructed, and the fault data set comprises historical fault data of a large power grid and historical fault data of a backbone optical communication system; the fault data set is processed through a neural network model, a knowledge reasoning network chain is obtained, and the knowledge reasoning network chain comprises fault information of interaction between the large power grid and the backbone optical communication system; updating the operation fault relationship knowledge base of the large power grid and the backbone optical communication system by using the knowledge reasoning network chain; and carrying out early warning on operation faults of the large power grid and backbone optical communication system based on the updated operation fault relationship knowledge base. The technical problems that alarm information of a large power grid and a backbone optical communication system is dispersed, and isolated early warning response lags are solved.

Description

Technical Field

[0001] The present application relates to the field of power system fault warning, and in particular to a method and system for early warning of operation faults in a large power grid and a backbone optical communication system. Background Art

[0002] As the second physical network that coexists with the power grid, the power communication network is an important support for the safe, stable and economic operation of the power grid. With the help of abundant power transmission line resources, the power supply company has built a backbone network based on optical fiber communication by adopting the "cable + optical cable" method; it has built an integrated space-ground communication network by adopting optical fiber communication, carrier communication, wireless communication, satellite communication and other methods to meet the comprehensive coverage, real-time online, intelligent and efficient power business communication needs.

[0003] However, at present, the alarm information of large power grids and backbone optical communication systems is scattered, isolated, and the early warning response is delayed, and no effective solution has been proposed yet. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention proposes a method and system for early warning of operation failures of a large power grid and a backbone optical communication system.

[0005] The technical solution of the present invention is as follows:

[0006] On the one hand, the present invention provides a method for early warning of operation failure of a large power grid and a backbone optical communication system, comprising the following steps:

[0007] Constructing a fault data set, wherein the fault data set includes historical fault data of a large power grid and historical fault data of a backbone optical communication system;

[0008] Processing the fault data set using a neural network model to obtain a knowledge reasoning network chain, wherein the knowledge reasoning network chain includes fault information of interactions between a large power grid and a backbone optical communication system;

[0009] The knowledge base of the operational fault relationship between the large power grid and the backbone optical communication system is updated using the knowledge reasoning network chain;

[0010] Based on the updated operation fault relationship knowledge base, early warning of operation faults in large power grids and backbone optical communication systems is provided.

[0011] As a preferred implementation, the neural network model is trained by the following method:

[0012] Use the fault data set as the training data set;

[0013] Extracting feature data from the training data set, the feature data including time series features, device state features, event features, and correlation features between a large power grid and a backbone optical communication system;

[0014] Labeling the characteristic data with data labels, wherein the data labels include fault type, fault severity, and causal relationship between faults;

[0015] The neural network model is trained based on the feature data and the data labels.

[0016] As a preferred implementation, the step of processing the fault data set using a neural network model to obtain a knowledge reasoning network chain includes:

[0017] Inputting the fault data set into the neural network model for processing to generate a feature representation of each data sample in the fault data set, wherein the feature representation includes the fault type, the fault severity, and the causal relationship between the faults;

[0018] Analyze the correlation between the feature representations of each data sample and establish the interaction relationship between the large power grid and the backbone optical communication system;

[0019] The interaction relationship between the large power grid and the backbone optical communication system is integrated into the knowledge graph to generate the knowledge reasoning network chain.

[0020] As a preferred implementation, the step of early warning of operation failures of the large power grid and the backbone optical communication system based on the updated operation failure relationship knowledge base includes:

[0021] Obtain fault warning information;

[0022] Compare the fault alarm information with the entries in the updated operation fault relationship knowledge base to determine the historical fault case that is closest to the corresponding fault alarm information;

[0023] Evaluate the risk level of the fault warning information according to the most recent historical fault case;

[0024] When the risk level meets the preset conditions, early warning notification information and response measures or plans corresponding to the fault alarm information are generated.

[0025] As a preferred implementation, the step of comparing the fault warning information with the entries in the updated operation fault relationship knowledge base is specifically as follows:

[0026] Convert the fault warning information and the entries in the updated operation fault relationship knowledge base into feature vectors respectively;

[0027] Calculating the cosine similarity between the feature vector of the fault warning information and the feature vector of the entry in the operation fault relationship knowledge base;

[0028] The entry corresponding to the maximum cosine similarity is determined as the historical fault case that is closest to the fault alarm information.

[0029] As a preferred implementation, evaluating the risk level of the fault warning information according to the closest historical fault case includes:

[0030] Determine the risk level corresponding to the closest historical failure case;

[0031] The risk level corresponding to the closest historical failure case is used as the risk level of the failure alarm information.

[0032] As a preferred implementation, the step of updating the knowledge base of the operation fault relationship between the large power grid and the backbone optical communication system by using the knowledge reasoning network chain includes:

[0033] Establish the connection between the knowledge reasoning network chain and the operation fault relationship knowledge base;

[0034] Inserting the fault information of the interaction between the large power grid and the backbone optical communication system into the operation fault relationship knowledge base;

[0035] If the same fault information as that in the knowledge reasoning network chain exists in the operation fault relationship knowledge base, the same fault information originally in the operation fault relationship knowledge base is deleted.

[0036] On the other hand, the present invention also provides a large power grid and backbone optical communication system operation fault warning system, including: a front-end display device, configured to receive fault alarm information, and display warning notification information and response measures or plans corresponding to the fault alarm information; a processor, connected to the front-end display device, configured to execute the large power grid and backbone optical communication system operation fault warning method described in any embodiment of the present invention.

[0037] On the other hand, the present invention further proposes an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for early warning of operation failures of a large power grid and a backbone optical communication system as described in any embodiment of the present invention is implemented.

[0038] On the other hand, the present invention further proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the large power grid and backbone optical communication system operation fault warning method as described in any embodiment of the present invention.

[0039] The present invention adopts the method of constructing a fault data set; processing the fault data set by using a neural network model to obtain a knowledge reasoning network chain, wherein the knowledge reasoning network chain includes the fault information of the interaction between the large power grid and the backbone optical communication system; updating the knowledge base of the operation fault relationship between the large power grid and the backbone optical communication system by using the knowledge reasoning network chain; and warning the operation fault of the large power grid and the backbone optical communication system based on the updated operation fault relationship knowledge base. The processed operation fault candidate data set is processed by the neural network model to obtain the knowledge reasoning network chain, and the factors related to the failure of the large power grid and the backbone optical communication system are found. The obtained training result set is put into the operation fault relationship knowledge base of the large power grid and the backbone optical communication system for one-to-one matching, and the development context of the mutual influence between the power grid and the communication system is revealed and the analysis result is obtained, thereby completing the deduction and warning of the risk failure of the large power grid and the backbone optical communication system, thereby achieving the technical effect of making the failure of the large power grid and the backbone optical communication system within a controllable range and comprehensively improving the stability and reliability of the operation of the power system.

[0040] Additional aspects and advantages of the present invention will be set forth in the following description, and some of them will be apparent from the description, or may be understood by practicing the present invention. In addition, the various aspects and advantages of the present invention may be realized and obtained by the method steps and combinations particularly pointed out in the appended claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a flow chart of a method for early warning of operation failure of a large power grid and a backbone optical communication system according to an embodiment of the present application;

[0042] Figure 2 It is a structural block diagram of a large power grid and backbone optical communication system operation fault early warning system according to an embodiment of the present application;

[0043] Figure 3 Schematic diagram of the structure of the electronic device of this embodiment. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] It should be understood that the step numbers used in this document are only for convenience of description and are not intended to limit the order in which the steps are executed.

[0046] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0047] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0048] The term "and / or" means and includes any and all possible combinations of one or more of the associated listed items.

[0049] In order to better understand the embodiments of the present application, the technical terms involved in the embodiments of the present application are explained as follows:

[0050] The large power grid, also known as the wide area power grid or national power grid, refers to the power transmission and distribution network covering a wide geographical area. It consists of power stations, substations, transmission lines, and related control and protection systems, designed to achieve large-scale, long-distance power transmission.

[0051] Backbone optical communication system refers to the core part of the telecommunications network used for long-distance, high-capacity data transmission. It usually connects major cities or regions and forms the backbone of national or international networks.

[0052] In the related art, there are problems of scattered alarm information between large power grid and backbone optical communication system, isolated early warning response lag. In order to solve this problem, the embodiments of the present application provide relevant solutions, which are described in detail below.

[0053] Figure 1 is a flow chart of a method for early warning of operation failures of a large power grid and a backbone optical communication system according to an embodiment of the present application, such as Figure 1 As shown, the method comprises the following steps:

[0054] Step S102, constructing a fault data set, wherein the fault data set includes: historical fault data of the large power grid and historical fault data of the backbone optical communication system.

[0055] In the embodiments of the present application, historical fault data of the large power grid can be collected from the monitoring system, data acquisition and monitoring control system, energy management system, etc. of the power company. Historical fault data of the backbone optical communication system can be collected from the network management system, alarm log, maintenance record, etc. of the telecommunications operator.

[0056] Step S104, using a neural network model to process the fault data set to obtain a knowledge reasoning network chain, wherein the knowledge reasoning network chain includes the fault information of the interaction between the large power grid and the backbone optical communication system.

[0057] In this step, different neural network architectures can be selected according to the characteristics of the problem. For time series data, one-dimensional convolutional neural network (1D CNN) and long short-term memory network (Long Short-Term Memory, LSTM) can be selected. If the dataset contains multiple types of data (such as time series data and text data), you can consider using a multimodal neural network to process different types of data simultaneously.

[0058] Step S106, using the knowledge reasoning network chain to update the knowledge base of the operational fault relationship between the large power grid and the backbone optical communication system.

[0059] The knowledge base of operational fault relationship between large power grid and backbone optical communication system is a structured database or data warehouse, which is specially used to store and manage fault information about the interaction between large power grid and backbone optical communication system. It contains detailed information such as historical fault cases, system status when the fault occurred, related environmental conditions, and impact scope.

[0060] Using the knowledge reasoning network chain to update the knowledge base of the operational fault relationship between the large power grid and the backbone optical communication system can ensure that the information in the knowledge base is up to date and can reflect the latest fault modes and interactions.

[0061] Step S108: issuing early warnings for operation failures of the large power grid and the backbone optical communication system based on the updated operation failure relationship knowledge base.

[0062] The above-mentioned technical scheme provided in the embodiment of the present application processes the processed operation fault candidate data set through a neural network model to obtain a knowledge reasoning network chain, finds the factors related to the faults of the large power grid and the backbone optical communication system, and puts the obtained training result set into the operation fault relationship knowledge base of the large power grid and the backbone optical communication system for one-to-one matching, reveals the development context of the mutual influence between the power grid and the communication system and obtains the analysis results, thereby completing the deduction and early warning of risk faults of the large power grid and the backbone optical communication system, thereby achieving the technical effect of making the faults of the large power grid and the backbone optical communication system within a controllable range and comprehensively improving the stability and reliability of the operation of the power system.

[0063] According to an optional embodiment of the present application, the neural network model is trained by the following method: obtaining a training data set, wherein the training data set includes: historical fault data of a large power grid and historical fault data of a backbone optical communication system; extracting feature data from the training data set, wherein the feature data includes: time series features, equipment status features, event features, and correlation features between the large power grid and the backbone optical communication system; annotating the feature data with data labels, wherein the data labels include: fault type, fault severity, and causal relationship between faults; and training the neural network model based on the feature data and the data labels.

[0064] The training data set used when training the neural network model is also composed of historical fault data of the large power grid and the historical fault data of the backbone optical communication system.

[0065] Then, extract features that are helpful for model training and analysis, mainly including the following types of features:

[0066] Time series features: For time series data, statistical features (such as mean, variance, maximum, minimum, etc.) and frequency domain features (such as Fourier transform coefficients) can be extracted.

[0067] Equipment status characteristics: including equipment working status, load conditions, temperature, humidity and other environmental parameters.

[0068] Event characteristics: including fault type, time, location, duration, etc.

[0069] Correlation features: Analyze the mutual influence between the large power grid and the backbone optical communication system, and extract relevant features.

[0070] Next, classify and label the data to facilitate subsequent model training and analysis. Data can be classified according to the type of fault, such as power line fault, transformer fault, fiber interruption, signal attenuation, etc. Label the fault according to its scope and severity, such as minor, moderate, severe, etc. Label the causal relationship between faults, such as whether a power fault caused a communication system outage.

[0071] Finally, the neural network model is trained based on the feature data and the annotated data labels.

[0072] According to an optional embodiment of the present application, step S104 is executed to process the fault data set using a neural network model to obtain a knowledge reasoning network chain, including the following steps: inputting the fault data set into the neural network model for processing to generate a feature representation of each data sample in the fault data set, wherein the feature representation includes: fault type, fault severity, and causal relationship between faults; analyzing the correlation between the feature representations to establish an interaction relationship between the large power grid and the backbone optical communication system; integrating the interaction relationship between the large power grid and the backbone optical communication system into the knowledge graph to generate a knowledge reasoning network chain.

[0073] In the embodiment of the present application, the knowledge reasoning network chain construction mainly includes the following steps:

[0074] Feature representation: Use the trained neural network model to generate feature representations (usually high-dimensional vectors) for each sample. These feature representations capture the key information of the sample.

[0075] Relationship modeling, by analyzing the similarity or correlation between these feature representations, the interaction relationship between the large power grid and the backbone optical communication system can be established. The Pearson correlation coefficient, Spearman rank correlation coefficient, etc. between different features can be calculated to evaluate their correlation. Machine learning models (such as random forest, XGBoost, etc.) can also be used to mine deep association relationships.

[0076] Knowledge graph integration integrates these relationships into a knowledge graph to form a knowledge reasoning network chain. You can use a graph database (such as Neo4j, ArangoDB, etc.) to store and manage these relationships and integrate them into a knowledge graph.

[0077] Through the above steps, a neural network-based knowledge reasoning network chain can be constructed to analyze the fault information between the large power grid and the backbone optical communication system. This knowledge reasoning network chain can not only identify the fault mode, but also reveal the mutual influence between systems, thereby improving the accuracy of fault detection and early warning.

[0078] In some optional embodiments of the present application, step S108 is executed to warn of operational failures of the large power grid and the backbone optical communication system based on the updated operational failure relationship knowledge base, which is achieved by the following method: obtaining fault alarm information; comparing the fault alarm information with the entries in the updated operational failure relationship knowledge base to determine the historical failure case closest to the fault alarm information; evaluating the risk level of the fault alarm information based on the closest historical failure case; and generating early warning notification information and response measures or plans corresponding to the fault alarm information when the risk level meets the preset conditions.

[0079] As an optional embodiment of the present application, the risk level of the fault alarm information is evaluated based on the closest historical failure case, which is achieved by the following method: determining the risk level corresponding to the closest historical failure case; and using the risk level corresponding to the closest historical failure case as the risk level of the fault alarm information.

[0080] When new alarm information is generated, it is compared with the entries in the operational fault relationship knowledge base using a similarity matching algorithm (such as cosine similarity or Euclidean distance). The closest historical case is found to reveal potential risk paths and development contexts. The risk level corresponding to the closest historical fault case is used as the risk level of the current fault alarm information. In addition, the risk level of the fault alarm information under the current conditions can be evaluated based on the matching results, combined with expert rules and historical experience. Through logical reasoning or probability models, the possible scope of impact and consequences are predicted. Once a high-risk situation is detected (for example, the risk level exceeds the preset level), the early warning mechanism is immediately triggered and a notification is sent to relevant personnel. And recommended response measures or plans are provided so that quick action can be taken to reduce losses.

[0081] Using similarity matching algorithms (such as cosine similarity or Euclidean distance) to compare alarm information with entries in the knowledge base can help identify the historical fault cases that are most similar to the current alarm. This helps to quickly locate potential fault causes and provide corresponding treatment suggestions.

[0082] As some optional embodiments of the present application, comparing the fault alarm information with the entries in the updated operation fault relationship knowledge base can be achieved by the following method: converting the fault alarm information and the entries in the updated operation fault relationship knowledge base into feature vectors respectively; calculating the cosine similarity between the feature vector of the fault alarm information and the feature vector of the entry in the operation fault relationship knowledge base; determining the entry corresponding to the maximum cosine similarity as the historical fault case closest to the fault alarm information.

[0083] In this embodiment, the alarm information is compared with the entries in the operation fault relationship knowledge base by calculating the cosine similarity. The main steps include:

[0084] Ensure that the newly received alarm information has been cleaned and standardized. Extract relevant fault entries from the operation fault relationship knowledge base and format them into a form suitable for similarity calculation. Convert the alarm information and entries in the operation fault relationship knowledge base into feature vectors. These features can include timestamps, device IDs, fault types, sensor readings, etc. Calculate similarity using cosine similarity and find the most similar historical fault entries based on the similarity score.

[0085] Cosine similarity is a method to measure the similarity between two vectors, especially in high-dimensional space. It determines the degree of similarity between two vectors by calculating the cosine value of the angle between them. The value range of cosine similarity is between -1 and 1, where 1 represents the exact same direction (i.e., completely similar), 0 represents orthogonal (i.e., unrelated), and -1 represents the exact opposite direction (i.e., completely dissimilar). That is, the larger the cosine similarity value, the more similar the two vectors are.

[0086] Through the above steps, the similarity matching algorithm can be used to effectively compare the alarm information with the entries in the knowledge base, thereby improving the accuracy and speed of fault detection and early warning.

[0087] In other optional embodiments of the present application, step S106 is executed to update the operational fault relationship knowledge base of the large power grid and the backbone optical communication system using the knowledge reasoning network chain, including: establishing a connection between the knowledge reasoning network chain and the operational fault relationship knowledge base; inserting the fault information of the interaction between the large power grid and the backbone optical communication system into the operational fault relationship knowledge base; if the operational fault relationship knowledge base contains the same fault information as that in the knowledge reasoning network chain, deleting the original identical fault information in the operational fault relationship knowledge base.

[0088] Before updating the operational fault relationship knowledge base, prepare the newly discovered fault information about the interaction between the large power grid and the backbone optical communication system in the knowledge reasoning network chain so that it can be updated to the existing knowledge base. Make sure that the format of the new data is compatible with the existing knowledge base. For example, if the knowledge base uses the Neo4j graph database, the new data needs to be converted into the form of nodes and edges.

[0089] When updating, establish a connection with the existing operational fault relationship knowledge base. If it is a Neo4j database, you can use the officially provided driver or client tool. Then insert the newly discovered fault information of the interaction between the large power grid and the backbone optical communication system into the operational fault relationship knowledge base. For existing records, if there is new information or more accurate information, update these records. Remove old records that are no longer valid to keep the knowledge base clean.

[0090] Through the above steps, the knowledge reasoning network chain is used to update the operation fault relationship knowledge base of the large power grid and the backbone optical communication system, so as to maintain the timeliness and accuracy of the operation fault relationship knowledge base. This can not only improve the ability of fault detection and early warning, but also provide more reliable data support for decision makers.

[0091] As some optional embodiments of the present application, executing step S102 to construct a fault data set includes the following steps: obtaining historical fault data of a large power grid and historical fault data of a backbone optical communication system, wherein the historical fault data includes at least one of the following: time of occurrence of the fault, identification number or location of the faulty equipment, fault type, fault description information, and fault impact range; performing data cleaning processing on the historical fault data, wherein the data cleaning processing at least includes: deleting duplicate data, processing missing values, and detecting outliers; and performing standardization processing on the cleaned historical fault data.

[0092] The historical fault data of large power grids mainly include the following data types: timestamp (fault occurrence time), fault equipment ID or location, fault type (such as line fault, transformer fault, circuit breaker tripping, etc.), fault description, impact scope (affected area or number of users) and maintenance records (fault handling process and results).

[0093] The historical fault data of the backbone optical communication system mainly includes the following data types: timestamp (fault occurrence time), fault equipment ID or location, fault type (such as fiber break, signal attenuation, equipment failure, etc.), fault description, impact scope (affected area or service) and maintenance record (fault handling process and results).

[0094] Next, the acquired historical fault data needs to be cleaned. Data cleaning is a key step to ensure data quality. Deduplication refers to deleting duplicate records in the data set. Processing missing values ​​means that for missing data, interpolation methods (such as linear interpolation, forward filling, etc.) can be used to fill them, or records with more missing values ​​can be directly deleted. Outlier detection is to identify and process outliers, which may be caused by sensor errors or other reasons.

[0095] Standardizing the cleaned historical fault data is to ensure that the timestamp format of all data is consistent and the units are the same. Data standardization can be carried out from the following aspects:

[0096] Timestamp unification: convert all timestamps to the same format (such as UTC time).

[0097] Unit unification: If the data comes from different systems, they may have different measurement units. It is necessary to unify the units of all related data.

[0098] Data formatting: Formatting data into a form suitable for further processing, such as CSV, JSON, or a database table.

[0099] Through the above steps, a high-quality fault dataset can be constructed for subsequent analysis, modeling, and knowledge reasoning. This dataset is the basis for training machine learning models and building knowledge reasoning network chains.

[0100] Figure 2 is a structural block diagram of a large power grid and backbone optical communication system operation fault warning system according to an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0101] The front-end display device 20 is configured to receive fault alarm information and display early warning notification information and response measures or plans corresponding to the fault alarm information.

[0102] According to an optional embodiment of the present application, the front-end display device 20 includes but is not limited to mobile terminal devices, computer devices, etc. The front-end display device 20 is mainly used for the front-end display of the background processing content, mainly including the display of large power grid and backbone communication network equipment fault retrieval information, equipment fault knowledge graph generation and statistical analysis functions. And receiving fault alarm information.

[0103] The processor 22 is connected to the front-end display device 20 and is configured to execute the above method.

[0104] It should be noted that Figure 2 The preferred implementation of the embodiment shown can be referred to Figure 1 The relevant description of the illustrated embodiment will not be repeated here.

[0105] The embodiment of the present application also provides an electronic device, comprising: at least one processor; and a memory connected to the at least one processor in communication. The memory stores a computer program executable by the at least one processor, and the computer program is used to enable the electronic device to perform the method of the embodiment of the present application when executed by the at least one processor.

[0106] An embodiment of the present application also provides a non-transitory machine-readable medium storing a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiment of the present application.

[0107] The embodiment of the present application also provides a computer program product, including a computer program, wherein the computer program, when executed by a processor of a computer, is used to cause the computer to execute the method of the embodiment of the present application.

[0108] refer to Figure 3, the structural block diagram of the electronic device that can be used as the server or client of the embodiment of the present application will now be described, which is an example of the hardware device that can be applied to various aspects of the present application. The electronic device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0109] like Figure 3 As shown, the electronic device includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 302 or a computer program loaded from a storage unit 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0110] Multiple components in the electronic device are connected to the I / O interface 305, including: an input unit 306, an output unit 307, a storage unit 308, and a communication unit 309. The input unit 306 can be any type of device that can input information to the electronic device, and the input unit 306 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device. The output unit 307 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 308 can include but is not limited to a disk, an optical disk. The communication unit 309 allows the electronic device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0111] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a CPU, a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above. For example, in some embodiments, the method embodiments of the present application may be implemented as a computer program, which is tangibly contained in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on an electronic device via a ROM 302 and / or a communication unit 309. In some embodiments, the computing unit 301 may be configured to perform the above method in any other appropriate manner (e.g., by means of firmware).

[0112] The computer program for implementing the method of the embodiment of the present application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of the present application embodiment, machine-readable medium can be a tangible medium that can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable signal medium can include but is not limited to electronic, magnetic, optical, electromagnetic or infrared systems, devices or equipment, or any suitable combination of the above. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0114] It should be noted that the term "including" and its variations used in the embodiments of the present application are open inclusions, that is, "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one other embodiment"; the term "some embodiments" means "at least some embodiments". The modifications of "one" and "multiple" mentioned in the embodiments of the present application are illustrative and not restrictive. Those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0115] 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 the embodiments of the present 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 laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0116] The various steps described in the method implementation methods provided in the embodiments of the present application can be performed in different orders and / or in parallel. In addition, the method implementation methods may include additional steps and / or omit the steps shown. The scope of protection of the present application is not limited in this respect.

[0117] The term "embodiment" in this specification refers to specific features, structures or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. The various embodiments in this specification are described in a related manner, and the same or similar parts between the various embodiments refer to each other. In particular, for the device, equipment, and system embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts refer to the partial description of the method embodiment.

[0118] The above-mentioned 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 patent protection. 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 scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for early warning of operation failures of a large power grid and a backbone optical communication system, characterized in that: The following steps are involved: Constructing a fault data set, wherein the fault data set includes historical fault data of a large power grid and historical fault data of a backbone optical communication system; Processing the fault data set using a neural network model to obtain a knowledge reasoning network chain, wherein the knowledge reasoning network chain includes fault information of interactions between a large power grid and a backbone optical communication system; The knowledge base of the operational fault relationship between the large power grid and the backbone optical communication system is updated using the knowledge reasoning network chain; Based on the updated operation fault relationship knowledge base, early warning of operation faults in large power grids and backbone optical communication systems is provided.

2. A method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 1, characterized in that: The neural network model is trained by the following method: Use the fault data set as the training data set; Extracting feature data from the training data set, the feature data including time series features, device state features, event features, and correlation features between a large power grid and a backbone optical communication system; Labeling the characteristic data with data labels, wherein the data labels include fault type, fault severity, and causal relationship between faults; The neural network model is trained based on the feature data and the data labels.

3. A method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 1 or 2, characterized in that: The step of processing the fault data set using a neural network model to obtain a knowledge reasoning network chain includes: Inputting the fault data set into the neural network model for processing to generate a feature representation of each data sample in the fault data set, wherein the feature representation includes the fault type, the fault severity, and the causal relationship between the faults; Analyze the correlation between the feature representations of each data sample and establish the interaction relationship between the large power grid and the backbone optical communication system; The interaction relationship between the large power grid and the backbone optical communication system is integrated into the knowledge graph to generate the knowledge reasoning network chain.

4. The method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 1, characterized in that: The step of early warning of operation failures of the large power grid and the backbone optical communication system based on the updated operation failure relationship knowledge base includes: Obtain fault warning information; Compare the fault alarm information with the entries in the updated operation fault relationship knowledge base to determine the historical fault case that is closest to the corresponding fault alarm information; Evaluate the risk level of the fault warning information according to the most recent historical fault case; When the risk level meets the preset conditions, early warning notification information and response measures or plans corresponding to the fault alarm information are generated.

5. The method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 4, characterized in that: The step of comparing the fault warning information with the entries in the updated operation fault relationship knowledge base is specifically as follows: Convert the fault warning information and the entries in the updated operation fault relationship knowledge base into feature vectors respectively; Calculating the cosine similarity between the feature vector of the fault warning information and the feature vector of the entry in the operation fault relationship knowledge base; The entry corresponding to the maximum cosine similarity is determined as the historical fault case that is closest to the fault alarm information.

6. The method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 4, characterized in that: Evaluate the risk level of the fault warning information according to the closest historical fault case, including: Determine the risk level corresponding to the closest historical failure case; The risk level corresponding to the closest historical failure case is used as the risk level of the failure alarm information.

7. The method for early warning of operation failure of a large power grid and a backbone optical communication system according to claim 1, characterized in that: The step of updating the knowledge base of the relationship between the operation failure of the large power grid and the backbone optical communication system by using the knowledge reasoning network chain comprises: Establish the connection between the knowledge reasoning network chain and the operation fault relationship knowledge base; Inserting the fault information of the interaction between the large power grid and the backbone optical communication system into the operation fault relationship knowledge base; If the same fault information as that in the knowledge reasoning network chain exists in the operation fault relationship knowledge base, the same fault information originally in the operation fault relationship knowledge base is deleted.

8. A large power grid and backbone optical communication system operation fault warning system, characterized in that: include: A front-end display device, configured to receive fault alarm information, and display early warning notification information and response measures or plans corresponding to the fault alarm information; A processor is connected to the front-end display device and is configured to execute the large power grid and backbone optical communication system operation fault warning method described in any one of claims 1 to 7.

9. An electronic device, comprising: A processor, and a memory storing a program, characterized in that the program includes instructions, which, when executed by the processor, enable the processor to execute the large power grid and backbone optical communication system operation fault warning method described in any one of claims 1 to 7.

10. A non-transitory machine-readable medium storing computer instructions, characterized in that: The computer instructions are used to enable the computer to execute the large power grid and backbone optical communication system operation failure early warning method according to any one of claims 1 to 7.

Images