CN117376107A - Intelligent network management method, system, computer equipment and medium - Google Patents
Intelligent network management method, system, computer equipment and medium Download PDFInfo
- Publication number
- CN117376107A CN117376107A CN202311592702.9A CN202311592702A CN117376107A CN 117376107 A CN117376107 A CN 117376107A CN 202311592702 A CN202311592702 A CN 202311592702A CN 117376107 A CN117376107 A CN 117376107A
- Authority
- CN
- China
- Prior art keywords
- network
- data
- equipment
- fault
- onu
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 88
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000003860 storage Methods 0.000 claims abstract description 9
- 238000010586 diagram Methods 0.000 claims description 42
- 230000006399 behavior Effects 0.000 claims description 19
- 238000010276 construction Methods 0.000 claims description 15
- 230000003287 optical effect Effects 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 10
- 238000003780 insertion Methods 0.000 claims description 10
- 230000037431 insertion Effects 0.000 claims description 10
- 230000007547 defect Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 7
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000007306 turnover Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000012546 transfer Methods 0.000 claims description 2
- 230000036541 health Effects 0.000 abstract description 6
- 230000008569 process Effects 0.000 abstract description 6
- 230000007704 transition Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000015556 catabolic process Effects 0.000 description 3
- 238000001816 cooling Methods 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000008033 biological extinction Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0677—Localisation of faults
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/077—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using a supervisory or additional signal
- H04B10/0771—Fault location on the transmission path
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04B—TRANSMISSION
- H04B10/00—Transmission systems employing electromagnetic waves other than radio-waves, e.g. infrared, visible or ultraviolet light, or employing corpuscular radiation, e.g. quantum communication
- H04B10/07—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems
- H04B10/075—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal
- H04B10/079—Arrangements for monitoring or testing transmission systems; Arrangements for fault measurement of transmission systems using an in-service signal using measurements of the data signal
- H04B10/0791—Fault location on the transmission path
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
- H04L41/065—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis involving logical or physical relationship, e.g. grouping and hierarchies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses an intelligent network management method, an intelligent network management system, computer equipment and a storage medium, wherein the method adopts acquired historical data and real-time data corresponding to a service system, and a knowledge graph and an intelligent management model of the service system are respectively constructed according to the historical data; inputting real-time data into an intelligent management model of a service system to monitor the service system and identify network faults; based on the identified network faults, positioning the network faults according to the knowledge graph and the fault processing experience data, and generating a processing scheme. The intelligent network management method provided by the application can accurately diagnose the network faults and generate the detailed report, can optimize the utilization efficiency of network resources, improves the overall network performance and user experience, simplifies the fault handling process and improves the fault handling efficiency. By paying attention to three state transitions of ONU equipment, complicated steps are omitted, and the health state of the network is better monitored.
Description
Technical Field
The present disclosure relates to the field of network management technologies, and in particular, to an intelligent network management method, system, computer device, and medium.
Background
In the existing network management environment, the problem that massive alarms cannot be automatically converged is faced, network management staff is required to manage multiple manufacturer network management platforms simultaneously, alarm information from different network management platforms is processed, and efficiency is remarkably low. In addition, in PON systems, ONUs are connected through splitters, resulting in a failure of a logical topology to match a physical topology perfectly. When the network fails and generates an alarm, comprehensive analysis is still needed depending on network link information manually recorded by operation and maintenance personnel, and the mode of relying on manual decision has the risk of high error rate.
Disclosure of Invention
The application provides an intelligent network management method, system, computer equipment and medium, which are used for solving the technical problems that alarm information in the existing network management cannot be converged, the efficiency is low and the accuracy is low, realizing rapid and accurate network fault identification, providing an effective fault processing scheme, realizing automatic convergence of alarm and improving the efficiency of fault processing.
In order to solve the above technical problems, in a first aspect, the present application provides an intelligent network management method, where the method includes:
Acquiring historical data and real-time data corresponding to a service system, wherein the data at least comprises network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience data, log records and service system information;
constructing a knowledge graph according to the network equipment attribute relation data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearing relationship;
constructing a business system intelligent management model according to the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log recorded historical data;
inputting the real-time data into the intelligent management model of the service system to monitor the service system and identify network faults;
and positioning the faults according to the knowledge graph and the fault processing experience data based on the identified network faults, and generating a processing scheme.
Preferably, the constructing a knowledge graph includes:
preprocessing the network equipment attribute relation data and the service system information;
Based on the preprocessed network equipment attribute relation data and service system information, extracting a physical connection relation and a logical connection relation between the network equipment and a mapping relation between a service system and equipment;
constructing a network topology structure according to the physical connection relation, the logical connection relation and the mapping relation between the service system and the equipment;
based on the network topology structure, analyzing the matching degree of the physical connection relation and the logical connection relation between network devices and the link bandwidth and the performance of the network devices so as to determine the service path bearing relation;
and associating the network topological structure with the service path bearing relation to construct the knowledge graph.
Preferably, the building the intelligent management model of the service system includes:
preprocessing the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log recorded historical data, and extracting features;
constructing an intelligent business system management model based on a neural network model, wherein the intelligent business system management model comprises a classification module and a regression prediction module;
And training, testing, evaluating and optimizing the intelligent management model of the service system according to the extracted characteristics.
Preferably, the locating the fault based on the identified network fault according to the knowledge graph and the fault processing experience data includes:
establishing a fault conduction relation diagram between network equipment according to the knowledge graph and the fault processing experience data;
based on the identified network faults, adopting root cause reasoning to perform reverse reasoning in the fault conduction relation diagram, and sequentially finding out all equipment related to the network faults;
determining paths and key nodes of network faults through reverse reasoning based on all the devices related to the network faults;
and positioning equipment or components which cause the network failure according to the path and the key nodes of the network failure.
Preferably, the method further comprises:
the method comprises the steps of obtaining historical data and real-time data of ONU equipment, wherein the historical data and the real-time data of the ONU equipment at least comprise: performance index data of ONU equipment, state index data of ONU equipment, light receiving power of ONU equipment and channel light emitting power of PON light port;
Constructing an ONU equipment normal behavior model and an ONU equipment fault conduction relation diagram according to the historical data of the ONU equipment;
inputting real-time data of the ONU equipment into a normal behavior model of the ONU equipment, and identifying ONU equipment faults;
and positioning the ONU equipment faults by adopting root cause reasoning based on the ONU equipment fault conduction relation diagram.
Preferably, the constructing an ONU device normal behavior model and an ONU device fault conductance relation graph according to the historical data of the ONU device includes:
obtaining a difference value of the received light power of the ONU equipment minus the channel light emitting power of the PON optical port, obtaining an insertion loss value according to the difference value, and judging the arrangement sequence of the ONU equipment on a link according to the insertion loss value;
acquiring the bearing relation between ONU equipment and a PON optical port according to the arrangement sequence;
constructing an ONU equipment normal behavior model according to the bearing relation, the performance index data of the ONU equipment and the state index data of the ONU equipment;
and constructing an ONU equipment fault conduction relation diagram according to the bearing relation.
Preferably, the positioning the ONU device fault based on the ONU device fault conduction relationship diagram by root cause reasoning includes:
Based on the ONU equipment fault conduction relation diagram and a protection mechanism existing in a network, adopting root cause reasoning to sequentially find all ONU equipment related to the ONU equipment fault;
and judging the current state of all ONU equipment related to the ONU equipment fault, and monitoring the state turnover of the ONU equipment according to a judging result to obtain the defect eliminating state of the ONU equipment.
In a second aspect, the present application further provides an intelligent network management system, the system including:
the system comprises a data acquisition unit, a knowledge graph construction unit, a business system intelligent management model construction unit, a fault identification unit and a patrol positioning unit;
the data acquisition unit: the method comprises the steps of acquiring historical data and real-time data corresponding to a service system, wherein the data at least comprise network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience data, log records and service system information;
the knowledge graph construction unit is used for constructing a knowledge graph according to the network equipment attribute relation data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearing relationship;
The business system intelligent management model construction unit is used for constructing a business system intelligent management model according to the network equipment attribute relation data, the network performance index data, the network equipment state index data, the network security index data and the log record history data;
the fault identification unit is used for inputting the real-time data into the intelligent management model of the service system so as to monitor the service system and identify network faults;
the inspection locating unit is used for locating the faults according to the knowledge graph and the fault processing experience data based on the identified network faults and generating a processing scheme.
In a third aspect, the present application also provides a computer device comprising a memory, a processor, and a transceiver, connected by a bus; the memory is used to store a set of computer program instructions and data and to transfer the stored data to the processor, which executes the program instructions stored in the memory to perform the method described above.
In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored therein, which when executed, implements the method described above.
The application provides an intelligent network management method, an intelligent network management system, computer equipment and a storage medium, wherein the method adopts acquired historical data and real-time data corresponding to a service system, and a knowledge graph and an intelligent management model of the service system are respectively constructed according to the historical data; inputting real-time data into an intelligent management model of a service system to monitor the service system and identify network faults; based on the identified network faults, positioning the network faults according to the knowledge graph and the fault processing experience data, and generating a processing scheme. The intelligent network management method provided by the application can accurately diagnose the network faults and generate the detailed report, can optimize the utilization efficiency of network resources, improves the overall network performance and user experience, simplifies the fault handling process and improves the fault handling efficiency. By paying attention to three state transitions of ONU equipment, complicated steps are omitted, and the health state of the network is better monitored.
Drawings
FIG. 1 is a schematic diagram of steps of an intelligent network management method according to a preferred embodiment of the present application;
FIG. 2 is a schematic diagram of steps of a knowledge graph construction method according to a preferred embodiment of the present application;
FIG. 3 is a schematic diagram of steps of a method for constructing an intelligent management model of a service system according to a preferred embodiment of the present application;
FIG. 4 is a schematic diagram of steps of a fault location method provided in a preferred embodiment of the present application;
fig. 5 is a schematic diagram of method steps for monitoring and early warning of ONU devices according to a preferred embodiment of the present application;
fig. 6 is a schematic diagram of method steps for constructing an ONU device normal behavior model and an ONU device fault conduction relationship diagram according to a preferred embodiment of the present application;
fig. 7 is a schematic diagram of method steps for locating an ONU equipment fault according to a preferred embodiment of the present application;
FIG. 8 is a schematic diagram of a federal learning aggregation optimization system for power data sharing according to a preferred embodiment of the present application;
fig. 9 is a schematic diagram of a computer device according to a preferred embodiment of the present application.
Detailed Description
The following detailed description of the embodiments of the present application is provided for illustrative purposes only and is not to be construed as limiting the application, including the drawings, which are for reference and description only, and do not limit the scope of the patent application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In order to solve the technical problems that alarm information cannot be converged, the efficiency is low and the accuracy is low in the existing network management, the embodiment of the application provides an intelligent network management method, achieves rapid and accurate network fault identification, provides an effective fault processing scheme, achieves automatic convergence of alarms and improves the efficiency of fault processing.
Referring to fig. 1, in an embodiment of the present application, an intelligent network management method is provided, where the method includes:
s1, acquiring historical data and real-time data corresponding to a service system, wherein the data at least comprise network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience data, log records and service system information.
S2, constructing a knowledge graph according to the network equipment attribute relation data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearer relationships.
S3, constructing an intelligent management model of the service system according to the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log record history data.
S4, inputting the real-time data into the intelligent management model of the service system to monitor the service system and identify network faults.
S5, positioning the faults based on the identified network faults according to the knowledge graph and the fault processing experience data, and generating a processing scheme.
In the embodiment of the application, the data corresponding to different service systems are automatically collected through an automation technology and a machine learning and deep learning algorithm, wherein the data comprises network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience, log records, service system information and the like for supporting the operation of the service systems.
The network equipment attribute relation data comprises information such as a model number, an IP address and the like related to the network equipment; the network device status index data includes: CPU utilization, memory utilization, temperature, etc.; the network performance index data includes: bandwidth utilization, time delay, packet loss rate, etc.; the network security index data includes: firewall interception times, abnormal flow alarming times and the like.
Further, according to the obtained network equipment attribute relationship data and service system information, a knowledge graph is constructed, wherein the knowledge graph comprises the bearing, sharing and protection between the network equipment and the service system, and for the construction of the knowledge graph, as shown in fig. 2, the method specifically comprises the following steps:
S201, preprocessing the network equipment attribute relation data and the service system information.
S202, extracting a physical connection relation and a logical connection relation between network devices and a mapping relation between a service system and the devices based on the preprocessed network device attribute relation data and service system information.
S203, constructing a network topology structure according to the physical connection relation, the logical connection relation and the mapping relation between the service system and the equipment.
S204, based on the network topology structure, analyzing the matching degree of the physical connection relation and the logic connection relation between the network devices and the link bandwidth and the performance of the network devices so as to determine the service path bearing relation.
S205, associating the network topological structure with the service path bearing relation to construct the knowledge graph.
In the application, the network equipment attribute relation data and the service system information are required to be subjected to duplication removal, cleaning and formatting operations so as to remove redundant information and process abnormal data, so that the data has a unified standardized format, and the accuracy, the integrity and the consistency of the data are ensured.
Further, through natural language processing technology, entities such as network equipment, service, faults and the like involved in the data are identified, and unique identification symbols are allocated to the entities. According to the attribute characteristics of different entities, extracting the attribute information related to the different entities, such as the model number of the network equipment, the IP address, the type of the service system, the fault description and the like.
And automatically extracting the physical connection relation and the logical connection relation existing between the entities and the mapping relation between the service system and the network equipment through text mining and machine learning technologies.
And associating the entity, the attribute and the relation information to form a knowledge graph, wherein the network topology can be specifically represented based on a graph structure, wherein the equipment can be represented as a node, the connection relation can be represented as an edge, and the physical connection relation, the logical connection relation and the mapping relation between the service system and the equipment are fully considered to construct a complete network topology structure.
Further, the network topology structure needs to be optimized, the matching degree of the physical connection relation and the logical connection relation between the network devices, the link bandwidth and the network device performance is analyzed, the point positions which cannot meet the matching requirement are manually processed to determine the service path bearing relation of the service system in the network, the network topology structure and the service path bearing relation are associated, and the resource utilization rate of the network topology structure is further estimated and optimized.
And finally, correlating the constructed network topology with other service system related information to construct a complete knowledge graph.
The network topology structure is used for supporting analysis of path bearing relation between network equipment and service, and through modeling and analysis of the network topology structure, utilization efficiency of network resources can be accurately estimated and optimized, an intuitive graphical interface is provided, and a user can clearly know the running state and the topology structure of the whole network, so that unified operation and maintenance experience is provided.
Further, an intelligent management model of the service system is constructed according to the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the history data of the log record. The model is mainly used for monitoring and analyzing the network through data corresponding to the service system collected in real time and identifying faults, and the construction of the intelligent management model of the service system comprises the following steps of:
s301, preprocessing the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log recorded historical data, and extracting features.
S302, constructing an intelligent business system management model based on the neural network model, wherein the intelligent business system management model comprises a classification module and a regression prediction module.
S303, training, testing, evaluating and optimizing the intelligent management model of the service system according to the extracted characteristics.
In the method, firstly, preprocessing, including data cleaning, denoising and normalization processing, is required to be performed on collected network equipment attribute relation data, network equipment state index data, network performance index data, network security index data and log recorded historical data so as to ensure the quality and stability of the data. Further, feature extraction is performed on the processed data to extract key information of fault classification and prediction.
And constructing an intelligent management model of the business system by using a machine learning algorithm or a deep learning model, wherein the model comprises a classification module and a regression prediction module so as to classify and predict data.
According to the extracted characteristics of the historical data, training, testing, evaluating and optimizing the intelligent management model of the service system to improve the accuracy and generalization capability of the model and prevent the over-fitting and under-fitting of the model.
Real-time data corresponding to the service system obtained automatically through an automation technology is input into the intelligent management model of the service system, the real-time data is analyzed through the intelligent management model of the service system, so that the service system is monitored, network faults are identified, and early warning is carried out.
By monitoring and analyzing the real-time data, network faults can be identified more quickly and accurately, and high availability and stability of the service system are ensured.
Further, based on the identified network faults, positioning the faults according to the network topology structure and the fault processing experience data, and generating corresponding fault processing schemes or directly performing automatic processing. In the present application, the method for locating the fault, as shown in fig. 4, includes the following steps:
s501, establishing a fault conduction relation diagram between network devices according to the knowledge graph and the fault processing experience data.
S502, based on the identified network faults, adopting root cause reasoning to perform reverse reasoning in the fault conduction relation diagram, and sequentially finding all equipment related to the network faults.
S503, determining a path and key nodes of the network fault through reverse reasoning based on all the devices related to the network fault.
S504, positioning equipment or components causing network faults according to the paths and the key nodes of the network faults.
In the embodiment of the application, a fault conduction relation diagram between network devices is constructed according to the network topology structure and the fault processing experience data, and the root cause of the fault is calculated according to the fault conduction relation diagram. Specifically, according to the identified network faults, reverse reasoning is carried out in the fault conduction relation diagram by adopting root cause reasoning, and all equipment related to the faults are sequentially found. Based on all the devices related to the fault, the path and the key point of the fault are determined through reverse reasoning, and the specific device or component causing the fault is finally positioned. Finally, the fault locating result is displayed to operation and maintenance personnel in real time, so that the operation and maintenance personnel can be helped to locate and solve the faults rapidly.
In the embodiment of the application, the method further comprises the generation of a report, and week, month and year reports can be generated according to the needs according to the historical data and the real-time data corresponding to the acquired service system, and the format of the report can be set in advance according to the needs, including historical data analysis, real-time data analysis and comparison analysis. In terms of historical analysis, historical data is counted and analyzed to learn the operating state and performance level of the network device over a period of time. In the aspect of real-time analysis, current data are monitored and analyzed in real time, and abnormal conditions or potential problems of network equipment are found in time. And comparing the historical data with the current data to find out the change trend of the equipment performance and whether the equipment performance is abnormal or not. On the basis, the historical data and the real-time data can be processed by technical methods such as data mining, statistical analysis, machine learning and the like so as to extract useful information and characteristics and timely know the health condition and performance of the network equipment.
In this embodiment of the present application, the method further includes monitoring and early warning on the ONU device, specifically, as shown in fig. 5, including the following steps:
S01, acquiring historical data and real-time data of ONU equipment, wherein the historical data and the real-time data of the ONU equipment at least comprise: performance index data of the ONU equipment, state index data of the ONU equipment, light receiving power of the ONU equipment and channel light emitting power of a PON light port.
S02, constructing an ONU equipment normal behavior model and an ONU equipment fault conduction relation diagram according to the historical data of the ONU equipment.
S03, inputting the real-time data of the ONU equipment into the ONU equipment normal behavior model, and identifying the ONU equipment faults.
S04, positioning the ONU equipment faults by adopting root cause reasoning based on the ONU equipment fault conduction relation diagram.
The ONU equipment fault alarm management occupies an important position in EPON network management, acquires historical data and real-time data of ONU equipment, and at least comprises the following steps: performance index data of the ONU equipment, state index data of the ONU equipment, light receiving power of the ONU equipment and channel light emitting power of a PON light port. Constructing an ONU equipment normal behavior model and an ONU equipment fault conduction relation diagram according to the collected historical data, wherein the ONU equipment normal behavior model is used for carrying out fault identification and early warning on the ONU equipment through real-time data of the ONU equipment; the ONU equipment fault conduction relation diagram is used for positioning and monitoring the ONU equipment faults.
The key service index of the EPON is the state of the ONU equipment, the chain of fault transmission from the movable ring to the PON optical port is very long, and the factors such as protection relation, ONU equipment arrangement sequence and the like are required to be overlapped. Complex service implementation can be simplified on a unified bottom layer model, and ONU equipment state management of all manufacturers can be realized once only by establishing an ONU equipment fault conduction relation diagram and realizing ONU equipment ordering through link insertion loss. In the embodiment of the application, an ONU device normal behavior model and an ONU device fault conduction relationship diagram are constructed, as shown in fig. 6, and the method includes the following steps:
s021, obtaining the difference value of the light receiving power of the ONU equipment minus the channel light emitting power of the PON light port, obtaining an insertion loss value according to the difference value, and judging the arrangement sequence of the ONU equipment on a link according to the insertion loss value.
S022, according to the arrangement sequence, acquiring the bearing relation between the ONU equipment and the PON optical port.
S023, constructing an ONU equipment normal behavior model according to the bearing relation, the performance index data of the ONU equipment and the state index data of the ONU equipment.
S024, constructing an ONU equipment fault conduction relation diagram according to the bearing relation.
The determination of ONU device status depends on two factors: the arrangement sequence of the ONU equipment on the link and the bearing relation between the ONU equipment and the PON optical port are strongly related, the channel luminous power of the PON optical port is subtracted by the receiving power of the ONU equipment to obtain an insertion loss value, and the insertion loss value is an ideal index for judging the arrangement sequence of the ONU equipment on the link and can be automatically ordered according to the insertion loss value. According to the arrangement sequence, the bearing relation between the ONU equipment and the PON optical port can be obtained.
In the embodiment of the application, after the normal behavior model of the ONU equipment and the ONU equipment fault conduction relation diagram are obtained, monitoring, fault identification and fault positioning are required to be performed on the ONU equipment according to the normal behavior model of the ONU equipment and the ONU equipment fault conduction relation diagram. And after inputting the real-time data of the ONU equipment into the ONU equipment normal behavior model, identifying the ONU equipment fault through the comparison operation of the ONU equipment normal behavior model. Based on the ONU device fault conduction relationship diagram, root cause reasoning is adopted to locate the ONU device fault, as shown in fig. 7, including the following steps:
s041, based on the ONU equipment fault conduction relation diagram and a protection mechanism existing in a network, adopting root cause reasoning to sequentially find all ONU equipment related to the ONU equipment fault.
S042, judging the current states of all ONU equipment related to the ONU equipment faults, and monitoring the state turnover of the ONU equipment according to the judging result to obtain the defect eliminating state of the ONU equipment.
The ONU equipment fault conduction relation diagram comprises alarm information, protection state and other related data of each physical element, and the alarm information comprises: alarm type, alarm level and alarm time. The current defect eliminating state of the ONU device can be primarily judged through the alarm information, but the current defect eliminating state of the ONU device needs to be determined by combining a protection mechanism existing in the network, such as backup connection or redundant device.
Wherein, combining with the protection mechanism existing in the network, the PON optical port protection relationship needs to be identified. When the protection relationship is identified to exist between PON optical ports, the reliability and connectivity of the network can be ensured through the backup connection or the redundant ONU equipment, and when faults or state changes occur, whether the network needs to be switched to the backup connection or the redundant ONU equipment can be judged according to the protection relationship so as to ensure the normal operation of the network.
The core problem of operation and maintenance is the extinction state of ONU devices, and as the network scale continues to expand, it becomes increasingly difficult to monitor the health state of the network by observing alarm changes. This is because alarms and faults are not in one-to-one relationship: some PON optical ports do not bear the service and report an alarm; a single failure typically generates multiple alarms; even if a protection mechanism exists, the occurrence of network alarms does not indicate service interruption, and the factors frequently lead to the conditions of missing report and false report. Under the background, three states and state turnover of the ONU equipment are directly concerned, and the complicated steps from alarming to state analysis can be omitted.
The three states of the ONU device include: normal, degraded and deficiency eliminated. The state flip is the dynamic transition of the three conditions of defect elimination, degradation and normal.
a) Eliminating the defects: when the ONU equipment fails, the state of the ONU equipment is changed into a defect eliminating state from the failure state after maintenance or processing. Whether the ONU is eliminated or not can be judged by monitoring relevant alarm information of fault recovery and corresponding processing records.
b) Degradation: when performance of an ONU is degraded or unstable, its state may transition from a normal state to a degraded state. And judging whether the ONU is in a degradation state or not by monitoring the change of performance index data of the ONU equipment, such as abnormal conditions of indexes of bandwidth utilization rate, packet loss rate, delay and the like.
c) Normal: the ONU is in a normal state without failure or performance problems. Whether the ONU is in a normal state can be judged by whether the performance index data of the ONU equipment is in a normal range.
Furthermore, in the embodiment of the application, alarm anti-shake can be realized through a time axis pipe manager to improve fault handling efficiency, alarm cooling delay processing time is set based on a time axis, namely, when an alarm is cleared, a clearing event is not sent immediately, but a configurable cooling time is waited, when the alarm is reported again in the waiting process, the original alarm is restarted, no new alarm is generated, and alarm shake caused by critical power fluctuation is eliminated. Through specific network verification, when the alarm cooling delay processing time is set to 20 minutes, the number of alarms to be focused can be reduced by 80%.
According to the intelligent network management method provided by the embodiment of the application, the historical data and the real-time data corresponding to the service system are automatically acquired by adopting an automation technology, and a knowledge graph and an intelligent management model of the service system are respectively constructed according to the historical data; inputting real-time data into an intelligent management model of a service system to monitor the service system and identify network faults; based on the identified network faults, positioning the network faults according to the knowledge graph base and fault processing experience data, and generating a processing scheme. The intelligent network management method provided by the application can accurately diagnose the network faults and generate the detailed report, can optimize the utilization efficiency of network resources, improves the overall network performance and user experience, simplifies the fault handling process and improves the fault handling efficiency. By paying attention to three state transitions of ONU equipment, complicated steps are omitted, and the health state of the network is better monitored.
Accordingly, as shown in fig. 8, based on the intelligent network management method, the embodiment of the present invention further provides an intelligent network management system, where the system includes: the system comprises a data acquisition unit 1, a knowledge graph construction unit 2, a business system intelligent management model construction unit 3, a fault identification unit 4 and a patrol positioning unit 5;
The data acquisition unit 1 is configured to acquire historical data and real-time data corresponding to a service system, where the data at least includes network device attribute relationship data, network device status index data, network performance index data, network security index data, fault handling experience data, log records, and service system information.
The knowledge graph construction unit 2 is configured to construct a knowledge graph according to the network device attribute relationship data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearer relationships.
The business system intelligent management model construction unit 3 is configured to construct a business system intelligent management model according to the network device attribute relationship data, the network performance index data, the network device state index data, the network security index data and the log recorded history data.
The fault recognition unit 4 is configured to input the real-time data into the intelligent management model of the service system, so as to monitor the service system and recognize a network fault.
The inspection location unit 5 is configured to locate the fault according to the knowledge graph and the fault processing experience data based on the identified network fault, and generate a processing scheme.
For a specific limitation of an intelligent network management system, reference may be made to the above limitation of an intelligent network management method, which is not repeated here. Those of ordinary skill in the art will appreciate that the various modules and steps described in connection with the embodiments disclosed herein may be implemented as hardware, software, or a combination of both, and to clearly illustrate the interchangeability of hardware and software, the steps and components of various embodiments have been described above generally in terms of functionality. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
As shown in fig. 9, a computer device provided in an embodiment of the present invention includes a memory, a processor, and a transceiver, which are connected by a bus; the memory is used for storing a set of computer program instructions and data and transmitting the stored data to the processor, and the processor executes the program instructions stored in the memory to perform the steps of the intelligent network management method described above.
Wherein the memory may comprise volatile memory or nonvolatile memory, or may comprise both volatile and nonvolatile memory; the processor may be a central processing unit, a microprocessor, an application specific integrated circuit, a programmable logic device, or a combination thereof. By way of example and not limitation, the programmable logic device described above may be a complex programmable logic device, a field programmable gate array, general purpose array logic, or any combination thereof.
In addition, the memory may be a physically separate unit or may be integrated with the processor.
It will be appreciated by those of ordinary skill in the art that the structure shown in fig. 9 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have the same arrangement of components.
In one embodiment, a computer readable storage medium is provided for storing one or more computer programs comprising program code for performing the steps of the intelligent network management method described above when the computer programs are run on a computer.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present invention, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, e.g., from one website, computer, server, or data center, via a wired (e.g., coaxial cable, fiber optic, digital subscriber line, or wireless (e.g., infrared, wireless, microwave, etc.) connection to another website, computer, server, or data center.
Those skilled in the art will appreciate that implementing all or part of the above described embodiment methods may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed, may comprise the steps of embodiments of the methods described above.
The intelligent network management method, system, computer equipment and storage medium provided in the embodiment aim at the technical problems that alarm information cannot be converged, efficiency is low and accuracy is low in the existing network management. According to the intelligent network management method, the historical data and the real-time data corresponding to the service system are automatically acquired by adopting an automation technology, and a knowledge graph and an intelligent management model of the service system are respectively constructed according to the historical data; inputting real-time data into an intelligent management model of a service system to monitor the service system and identify network faults; based on the identified network faults, positioning the network faults according to the knowledge graph base and the fault processing experience data, and generating a processing scheme. The intelligent network management method provided by the application can accurately diagnose the network faults and generate the detailed report, can optimize the utilization efficiency of network resources, improves the overall network performance and user experience, simplifies the fault handling process and improves the fault handling efficiency. By paying attention to three state transitions of ONU equipment, complicated steps are omitted, and the health state of the network is better monitored.
The foregoing examples represent only a few preferred embodiments of the present application, which are described in more detail and are not thereby to be construed as limiting the scope of the invention. It should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present invention, and such modifications and substitutions should also be considered to be within the scope of the present application. Therefore, the protection scope of the patent application is subject to the protection scope of the claims.
Claims (10)
1. An intelligent network management method, the method comprising:
acquiring historical data and real-time data corresponding to a service system, wherein the data at least comprises network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience data, log records and service system information;
constructing a knowledge graph according to the network equipment attribute relation data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearing relationship;
constructing a business system intelligent management model according to the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log recorded historical data;
Inputting the real-time data into the intelligent management model of the service system to monitor the service system and identify network faults;
and positioning the faults according to the knowledge graph and the fault processing experience data based on the identified network faults, and generating a processing scheme.
2. The intelligent network management method according to claim 1, wherein the constructing a knowledge graph includes:
preprocessing the network equipment attribute relation data and the service system information;
based on the preprocessed network equipment attribute relation data and service system information, extracting a physical connection relation and a logical connection relation between the network equipment and a mapping relation between a service system and equipment;
constructing a network topology structure according to the physical connection relation, the logical connection relation and the mapping relation between the service system and the equipment;
based on the network topology structure, analyzing the matching degree of the physical connection relation and the logical connection relation between network devices and the link bandwidth and the performance of the network devices so as to determine the service path bearing relation;
and associating the network topological structure with the service path bearing relation to construct the knowledge graph.
3. The intelligent network management method according to claim 1, wherein the constructing the intelligent management model of the service system comprises:
preprocessing the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log recorded historical data, and extracting features;
constructing an intelligent business system management model based on a neural network model, wherein the intelligent business system management model comprises a classification module and a regression prediction module;
and training, testing, evaluating and optimizing the intelligent management model of the service system according to the extracted characteristics.
4. The intelligent network management method according to claim 1, wherein said locating said fault based on said knowledge-graph and said fault handling experience data based on said identified network fault comprises:
establishing a fault conduction relation diagram between network equipment according to the knowledge graph and the fault processing experience data;
based on the identified network faults, adopting root cause reasoning to perform reverse reasoning in the fault conduction relation diagram, and sequentially finding out all equipment related to the network faults;
Determining paths and key nodes of network faults through reverse reasoning based on all the devices related to the network faults;
and positioning equipment or components which cause the network failure according to the path and the key nodes of the network failure.
5. The intelligent network management method according to claim 1, wherein the method further comprises:
the method comprises the steps of obtaining historical data and real-time data of ONU equipment, wherein the historical data and the real-time data of the ONU equipment at least comprise: performance index data of ONU equipment, state index data of ONU equipment, light receiving power of ONU equipment and channel light emitting power of PON light port;
constructing an ONU equipment normal behavior model and an ONU equipment fault conduction relation diagram according to the historical data of the ONU equipment;
inputting real-time data of the ONU equipment into a normal behavior model of the ONU equipment, and identifying ONU equipment faults;
and positioning the ONU equipment faults by adopting root cause reasoning based on the ONU equipment fault conduction relation diagram.
6. The intelligent network management method according to claim 5, wherein constructing an ONU device normal behavior model and an ONU device fault conductance relation graph according to the history data of the ONU device comprises:
Obtaining a difference value of the received light power of the ONU equipment minus the channel light emitting power of the PON optical port, obtaining an insertion loss value according to the difference value, and judging the arrangement sequence of the ONU equipment on a link according to the insertion loss value;
acquiring the bearing relation between ONU equipment and a PON optical port according to the arrangement sequence;
constructing an ONU equipment normal behavior model according to the bearing relation, the performance index data of the ONU equipment and the state index data of the ONU equipment;
and constructing an ONU equipment fault conduction relation diagram according to the bearing relation.
7. The power data sharing oriented federal learning aggregation optimization method according to claim 6, wherein the positioning the ONU device fault using root cause reasoning based on the ONU device fault conduction relationship diagram comprises:
based on the ONU equipment fault conduction relation diagram and a protection mechanism existing in a network, adopting root cause reasoning to sequentially find all ONU equipment related to the ONU equipment fault;
and judging the current state of all ONU equipment related to the ONU equipment fault, and monitoring the state turnover of the ONU equipment according to a judging result to obtain the defect eliminating state of the ONU equipment.
8. An intelligent network management system, the system comprising: the system comprises a data acquisition unit, a knowledge graph construction unit, a business system intelligent management model construction unit, a fault identification unit and a patrol positioning unit;
the data acquisition unit: the method comprises the steps of acquiring historical data and real-time data corresponding to a service system, wherein the data at least comprise network equipment attribute relation data, network equipment state index data, network performance index data, network safety index data, fault processing experience data, log records and service system information;
the knowledge graph construction unit is used for constructing a knowledge graph according to the network equipment attribute relation data and the service system information; the knowledge graph at least comprises: network topology and traffic path bearing relationship;
the business system intelligent management model construction unit is used for constructing a business system intelligent management model according to the network equipment attribute relation data, the network equipment state index data, the network performance index data, the network security index data and the log record history data;
the fault identification unit is used for inputting the real-time data into the intelligent management model of the service system so as to monitor the service system and identify network faults;
The inspection locating unit is used for locating the faults according to the knowledge graph and the fault processing experience data based on the identified network faults and generating a processing scheme.
9. A computer device, characterized by: the computer device comprises a memory, a processor and a transceiver, which are connected through a bus; the memory is used to store a set of computer program instructions and data and to transfer the stored data to the processor, which executes the program instructions stored in the memory to perform the method of any one of claims 1 to 7.
10. A computer-readable storage medium, characterized by: the computer readable storage medium having stored therein a computer program which, when executed, implements the method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311592702.9A CN117376107A (en) | 2023-11-27 | 2023-11-27 | Intelligent network management method, system, computer equipment and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311592702.9A CN117376107A (en) | 2023-11-27 | 2023-11-27 | Intelligent network management method, system, computer equipment and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117376107A true CN117376107A (en) | 2024-01-09 |
Family
ID=89396819
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311592702.9A Pending CN117376107A (en) | 2023-11-27 | 2023-11-27 | Intelligent network management method, system, computer equipment and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117376107A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118138442A (en) * | 2024-05-07 | 2024-06-04 | 广东名阳信息科技有限公司 | Network fault diagnosis method and system based on log data |
-
2023
- 2023-11-27 CN CN202311592702.9A patent/CN117376107A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118138442A (en) * | 2024-05-07 | 2024-06-04 | 广东名阳信息科技有限公司 | Network fault diagnosis method and system based on log data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110493042B (en) | Fault diagnosis method and device and server | |
US20220187815A1 (en) | Systems and methods for detecting and predicting faults in an industrial process automation system | |
US11792217B2 (en) | Systems and methods to detect abnormal behavior in networks | |
US11271795B2 (en) | Systems and methods for proactive network operations | |
US10649838B2 (en) | Automatic correlation of dynamic system events within computing devices | |
CN109787817B (en) | Network fault diagnosis method, device and computer readable storage medium | |
TWI741505B (en) | Topology processing method, device and system | |
US20200106662A1 (en) | Systems and methods for managing network health | |
US6604208B1 (en) | Incremental alarm correlation method and apparatus | |
US11348023B2 (en) | Identifying locations and causes of network faults | |
US20200021511A1 (en) | Performance analysis for transport networks using frequent log sequence discovery | |
US11894969B2 (en) | Identifying root causes of network service degradation | |
CN115118581B (en) | Internet of things data all-link monitoring and intelligent guaranteeing system based on 5G | |
CN112769605B (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
CN117376107A (en) | Intelligent network management method, system, computer equipment and medium | |
KR102367861B1 (en) | Apparatus, method and computer program for determining error of network equipment based on self-learning | |
CN112752172B (en) | Optical channel fault diagnosis method and system based on transfer learning | |
KR102418594B1 (en) | Ict equipment management system and method there of | |
Rafique et al. | TSDN-enabled network assurance: A cognitive fault detection architecture | |
US7822417B1 (en) | Method for predictive maintenance of a communication network | |
CN111988172B (en) | Network information management platform, device and security management method | |
US10432451B2 (en) | Systems and methods for managing network health | |
KR101520103B1 (en) | System and method for inference and surveillance of application fault of it service using functional partitioning | |
US11477070B1 (en) | Identifying root causes of network service degradation | |
CN113890814B (en) | Fault perception model construction and fault perception method and system, equipment and medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |