CN116827817A - Data link state monitoring method, device, monitoring system and storage medium - Google Patents
Data link state monitoring method, device, monitoring system and storage medium Download PDFInfo
- Publication number
- CN116827817A CN116827817A CN202310389968.7A CN202310389968A CN116827817A CN 116827817 A CN116827817 A CN 116827817A CN 202310389968 A CN202310389968 A CN 202310389968A CN 116827817 A CN116827817 A CN 116827817A
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- data link
- index data
- link
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims abstract description 186
- 230000005856 abnormality Effects 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims description 42
- 230000005540 biological transmission Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 22
- 230000008569 process Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 6
- 230000004044 response Effects 0.000 claims description 5
- 230000004807 localization Effects 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 8
- 238000012806 monitoring device Methods 0.000 abstract description 3
- 238000007726 management method Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 15
- 238000001816 cooling Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002349 favourable effect Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005553 drilling Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010792 warming Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0811—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking connectivity
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0829—Packet loss
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0823—Errors, e.g. transmission errors
- H04L43/0847—Transmission error
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0852—Delays
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/50—Testing arrangements
Abstract
The invention provides a data link state monitoring method, a data link state monitoring device, a data link state monitoring system and a storage medium. The method comprises the following steps: according to the type of the data link of the data center station, index data indicating the running state of each data link is obtained through the buried point; when determining that a certain data link is abnormal according to index data of each data link and a preset abnormality judgment model, obtaining an abnormality type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormality positioning model; acquiring quality index data corresponding to the data transmitted by the data link when the data are transferred among all layers of the data center station; and rechecking the initial positioning result of the abnormal type according to the quality index data, and determining the final positioning result of the abnormal type of the data link. The invention can accurately monitor the abnormal state of the data link, thereby being beneficial to improving the data service supporting capability of the data center station and being more beneficial to the exertion of the value of the data center station.
Description
Technical Field
The present invention relates to the field of data monitoring technologies, and in particular, to a method and apparatus for monitoring a data link state, a monitoring system, and a storage medium.
Background
With the advent of the large data age, more and more data has been generated, and for enterprises with more business systems, data is typically stored by way of data center integration. Along with the continuous collection and precipitation of enterprise high-value data in the data center, the requirements of each business system on the data service supporting capability of the data center in the aspects of data sharing, data interaction and the like are increasingly increased.
However, with the continuous progress of data center station construction, data resources are continuously enriched, the construction scale of data links is gradually increased and complicated, and the large and complicated data links are unfavorable for the stability of data quality of the data center station, so that the data service supporting capability of the data center station is affected. Therefore, accurately monitoring the abnormal state of the data link is important to improve the data service supporting capability of the data center station.
Disclosure of Invention
The embodiment of the invention provides a data link state monitoring method, a device, a monitoring system and a storage medium, which are used for solving the problem that for a data center station with a huge and complex data link, the abnormal state of the data link is difficult to accurately detect.
In a first aspect, an embodiment of the present invention provides a method for monitoring a data link status, including:
According to the type of the data link of the data center station, index data indicating the running state of each data link is obtained through the buried point;
when determining that a certain data link is abnormal according to index data of each data link and a preset abnormality judgment model, obtaining an abnormality type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormality positioning model;
acquiring quality index data corresponding to the data transmitted by the data link when the data are transferred among all layers of the data center station;
and rechecking the initial positioning result of the abnormal type according to the quality index data, and determining the final positioning result of the abnormal type of the data link.
In one possible implementation, the types of data links include data links transmitted at regular time and data links transmitted in real time;
the method for obtaining index data indicating the running state of each data link through the buried point according to the type of the data link of the data center station comprises the following steps:
if the type of the data link of the data center station is a data link of timing transmission, acquiring the time interval of data transmission, the data quantity of the data transmission and the response timeliness of the data link through the buried point;
If the type of the data link of the data center station is a data link of real-time transmission, the communication state of the data link, the unblocked state of the data link, the link resource utilization rate, the network delay information, the integrity information of the data transmission and the packet loss rate are obtained through the buried point.
In one possible implementation manner, the training process of the preset abnormality judgment model includes:
acquiring normal index data indicating that the operation state of the data link is normal and abnormal index data indicating that the operation state of the data link is abnormal;
grouping the normal index data and the abnormal index data according to the source of each data link;
calculating the ratio of the number of the normal index data to the number of the abnormal index data in each group, and recording the ratio as the copy multiple of the abnormal index data in the group;
copying the abnormal index data in each group according to the copy multiple of the abnormal index data in the group so as to form a training sample set according to all the normal index data and all the copied abnormal index data;
training the abnormality judgment model according to the training sample set to obtain a preset abnormality judgment model.
In one possible implementation manner, the obtaining, according to the index data corresponding to the data link and the preset abnormal location model, an initial location result of an abnormal type of the data link includes:
Dimensionless treatment is carried out on the index data to obtain first dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to the index data to obtain second dimensionless data;
calculating a first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data;
and inputting the first similarity into a preset abnormal positioning model, and determining an abnormal type initial positioning result of the data link.
In one possible implementation manner, the calculating the first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data includes:
according toCalculating a first similarity between the index data and the standard index data;
wherein s is the first similarity between the index data and the standard index data, y is the first dimensionless data, y max For the second dimensionless data corresponding to the maximum value in the standard index data corresponding to the index data, y min And the second dimensionless data corresponding to the minimum value in the standard index data corresponding to the index data.
In one possible implementation manner, the training process of the preset anomaly locating model includes:
Acquiring a plurality of pieces of abnormal index data indicating abnormal operation states of the data link;
dimensionless treatment is carried out on each piece of abnormal index data to obtain third dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to each piece of abnormal index data to obtain fourth dimensionless data;
calculating to obtain a second similarity between each piece of abnormal index data and the standard index data according to the third dimensionless data and the fourth dimensionless data so as to form an abnormal positioning training sample set;
training the abnormal positioning model according to the abnormal positioning training sample set to obtain a preset abnormal positioning model.
In one possible implementation manner, the rechecking the initial positioning result of the abnormal type according to the quality index data, and determining the final positioning result of the abnormal type of the data link includes:
determining a first probability that the data link is of various anomaly types according to the quality index data;
and determining an abnormal type final positioning result of the data link according to the first probability and the abnormal type initial positioning result.
In a second aspect, an embodiment of the present invention provides a data link status monitoring apparatus, including:
The first acquisition module is used for acquiring index data indicating the running state of each data link through the buried point according to the type of the data link of the data center station;
the processing module is used for obtaining an initial positioning result of the abnormal type of the data link according to the index data corresponding to the data link and a preset abnormal positioning model when determining that a certain data link is abnormal according to the index data of each data link and the preset abnormal judgment model;
the second acquisition module is used for acquiring quality index data corresponding to the data transmitted by the data link when the data are transferred among all layers of the data center station;
and the state monitoring module is used for rechecking the initial positioning result of the abnormal type according to the quality index data and determining the final positioning result of the abnormal type of the data link.
In a third aspect, an embodiment of the present invention provides a monitoring system, including a memory for storing a computer program and a processor for calling and running the computer program stored in the memory, to perform the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
In a fourth aspect, embodiments of the present invention provide a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method as described above in the first aspect or any one of the possible implementations of the first aspect.
The embodiment of the invention provides a data link state monitoring method, a device, a monitoring system and a storage medium, which can acquire different index data for different types of data links by acquiring index data indicating the running state of each data link through a buried point according to the type of the data link of a data center station, thereby being beneficial to accurately determining whether a certain data link is abnormal or not and the initial positioning result of the abnormal type of the certain data link. On the basis, when determining that a certain data link is abnormal according to index data of each data link and a preset abnormal judgment model, acquiring an abnormal type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormal positioning model, acquiring quality index data corresponding to the data transmitted by the data link when the data are circulated among layers of the data center station, rechecking the abnormal type initial positioning result according to the quality index data, and determining an abnormal type final positioning result of the data link.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an implementation of a method for monitoring a data link status according to an embodiment of the present invention;
FIG. 2 is a functional schematic diagram of buried point management according to an embodiment of the present invention;
FIG. 3 is a data flow chart of a data center station according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a data link status monitoring device according to an embodiment of the present invention;
fig. 5 is a schematic diagram of a monitoring system according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth such as the particular system architecture, techniques, etc., in order to provide a thorough understanding of the embodiments of the present invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of an implementation of a method for monitoring a data link status according to an embodiment of the present invention is shown, and details are as follows:
in step 101, index data indicating an operation state of each data link is obtained through the buried point according to the type of the data link of the station in the data.
Wherein, according to the transmission direction of the data link, the data link of the data center station can be divided into a transverse data link and a longitudinal data link. For example, the lateral data link may be a data transfer between a headquarter primary service system and a headquarter data center, or a data transfer between a subsection secondary service system and a subsection data center. The longitudinal data link may be a data transmission between a headquarter data center and a subsection data center. In this embodiment, the index data indicating the operation state of each data link is obtained through the buried point, which may be the index data indicating the operation state of each transverse data link or the index data indicating the operation state of each longitudinal data link, so that the two-stage data link state monitoring of the middle station in the headquarter data and the middle station in the branch data may be realized based on the index data indicating the operation state of each transverse data link and the index data indicating the operation state of each longitudinal data link.
The embedded point is a common data acquisition method for website analysis, index data indicating the running state of each data link is obtained through the embedded point, and the data acquisition is accurate, so that the subsequent rapid and accurate data link state monitoring is facilitated.
Alternatively, the types of data links may include data links transmitted in timing and data links transmitted in real time.
Accordingly, according to the type of the data link of the data center station, obtaining index data indicating the operation state of each data link through the buried point may include:
if the type of the data link of the data center station is a data link of timing transmission, acquiring the time interval of data transmission, the data quantity of the data transmission and the response timeliness of the data link through the buried point.
If the type of the data link of the data center station is a data link of real-time transmission, the communication state of the data link, the unblocked state of the data link, the link resource utilization rate, the network delay information, the integrity information of the data transmission and the packet loss rate are obtained through the buried point.
As shown in connection with fig. 2, since the data capacity of the data center of the enterprise is usually in units of PB or EB or higher, sometimes even higher order of unit capacity is reached. The amount of data sent from the branch data center to the headquarter data center via the data link is large, and the data link is divided into an offline data link for timing transmission and a streaming data link for real-time transmission, so that the buried point can be managed by the buried point when index data indicating the operation state of each data link is obtained by the buried point.
As shown in fig. 2, the embedded point management totally involves four objects, namely application management, embedded point demand management, event management and attribute management. The relationship between them is a top-down logical relationship. For example, in the embedded point demand management module of the system, an application name is screened out, and then all the embedded point demand lists of the data links under the selected application are correspondingly displayed, and when a single embedded point demand batch is selected, all the embedded point events under the batch are correspondingly displayed.
The application management function is mainly to bear the business product object and can correspond to a business system corresponding to the data center. When the point is buried, a new product point buried object needs to be created in the system, and then the later increased point buried requirement, event meta information and the like exist. The application management module can comprise basic functions such as application addition, deletion, editing and the like.
The embedded point requirement management function mainly bears embedded point requirement documents, and can achieve functions of creating requirements, editing requirements, drilling requirements, offline requirements and the like. In the buried demand management module, demands are managed according to batches, each buried demand has a unique batch number, and clicking on a single buried demand batch number can drill down directly to all event lists under the buried demand.
The event management function carries the meta information of the buried event which needs to be developed and is disassembled from all the buried requirements, and can realize the functions of creating the event, editing the event, logging-off the line event, searching the event, logging-on the line event and the like. The event is the minimum object unit of the buried point disassembly, each event in the event management module is required to be mounted on the corresponding buried point demand batch, and the system has no independent self-oscillation event. Thus, all applications, buried demand lots and events have mapping relations. When the buried point data is needed, the buried point management system searches the buried point demand lot, and the clear mapping relation provides an efficient way when the buried point meta-information is queried.
The attribute management function module carries common attributes such as data transmission rate, transmission port and the like. These commonalities may be registered at the attribute management module. When an event is newly established, the registered completed attribute can be directly quoted and bound to the event, and a large number of repeated filling works when the event attribute information is filled are reduced.
The embedded point management can also comprise an embedded point monitoring module, and the embedded point monitoring function carries the monitoring of all embedded point events and the results of task operation of the embedded point management system. The system comprises a monitoring function module for counting and displaying the whole embedded point application statistics, embedded point demand statistics, event statistics, effective online event statistics, abnormal embedded point event number, unprocessed embedded point demand/event number and the like, and is used for counting and displaying the management objects and the object running conditions of the whole system.
In this embodiment, since the data link may be divided into a data link that is transmitted in a timing manner and a data link that is transmitted in a real-time manner, the information to be collected by the buried point should also be different, so as to obtain different index data for different types of data links, thereby being beneficial to accurately determining whether a certain data link is abnormal or not and the initial positioning result of the abnormal type of a certain data link.
For example, for status awareness of data links for timing transmissions, the time interval of data transmissions, the amount of data transmitted each time, and whether to transmit data to headquarter data center in a timely manner according to system requirements may be emphasized (for example, may be characterized by the response timeliness of the data links). For state sensing of a data link transmitted in real time, it should be noted whether the data link is connected (i.e., the connected state of the data link), whether the data link is unblocked (i.e., the unblocked state of the data link), how much of the link resource utilization is, related information of network delay, whether the data transmission information is complete (i.e., the integrity information of data transmission), whether packet loss occurs (i.e., the packet loss rate), and the like, and meanwhile, the buried point of the data link transmitted in real time cannot affect the transmission work of the current data link.
In step 102, when determining that a certain data link is abnormal according to the index data of each data link and a preset abnormality determination model, obtaining an initial positioning result of the abnormality type of the data link according to the index data corresponding to the data link and the preset abnormality positioning model.
In this embodiment, after index data indicating the operation state of each data link is obtained through the buried point, whether each data link is abnormal is determined according to the index data of each data link and a preset abnormality determination model. And when a certain data link is abnormal, obtaining an abnormal type initial positioning result of the data link according to index data corresponding to the abnormal data link and a preset abnormal positioning model.
Optionally, the training process of the preset abnormality judgment model may include:
acquiring normal index data indicating that the operation state of the data link is normal and abnormal index data indicating that the operation state of the data link is abnormal; grouping the normal index data and the abnormal index data according to the source of each data link; calculating the ratio of the number of the normal index data to the number of the abnormal index data in each group, and recording the ratio as the copy multiple of the abnormal index data in the group; copying the abnormal index data in each group according to the copy multiple of the abnormal index data in the group so as to form a training sample set according to all the normal index data and all the copied abnormal index data; training the abnormality judgment model according to the training sample set to obtain a preset abnormality judgment model.
In this embodiment, the number of times that the data link is in a normal state is often greater than the number of times that the data link is in an abnormal state in the process of considering that the data link performs data resource transmission. Accordingly, the obtained normal index data is often larger than the abnormal index data, and thus the sample data amount in the training set for training the abnormal judgment model is unbalanced. If training is directly performed by using a training set with unbalanced sample data volume, the probability of missed judgment or misjudgment of an abnormal link by the obtained abnormal judgment model is greatly increased, and the accuracy of monitoring the data link state is further affected. In this embodiment, the data link is typically a data link between a different service system and a middle station of the branch data or a middle station of the headquarter data, or a data link between a middle station of the branch data and a middle station of the headquarter data, so that the normal index data and the abnormal index data can be grouped according to the source of the data link, so as to obtain a training sample set with balanced data volume based on the grouping result. Therefore, the preset abnormal judgment model obtained through training is more accurate, and the abnormal state of the data link is more favorably and accurately monitored.
Optionally, obtaining the initial positioning result of the abnormal type of the data link according to the index data corresponding to the data link and a preset abnormal positioning model may include:
Dimensionless treatment is carried out on the index data to obtain first dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to the index data to obtain second dimensionless data; calculating a first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data; inputting the first similarity into a preset abnormal positioning model, and determining an initial positioning result of the abnormal type of the data link.
In combination with the examples of the various index data given in step 101, it is known that different index data have different scales, the corresponding dimensions are different, the dimensions of each index data may have different value ranges, and there is often a large difference in numerical values. If the data with different dimensions are directly used without processing, errors of the preset abnormal positioning model can not be performed, and even if the preset abnormal positioning model can output positioning results, the accuracy of the preset abnormal positioning model is not high. Therefore, the present embodiment performs dimensionless treatment on the index data and the standard index data, respectively.
The standard index data refers to a value range of the corresponding index data. For example, the standard index data corresponding to the data amount of the data transmission may be 0MB to 4096MB, and the standard index data corresponding to the packet loss rate may be 0 permillage to 2 permillage. When the standard index data is dimensionless, the maximum value and the minimum value in the standard index data can be dimensionless respectively.
Optionally, calculating the first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data may include:
according toA first similarity of the index data and the standard index data is calculated.
Wherein s is the first similarity between the index data and the standard index data, y is the first dimensionless data, y max Is the second dimensionless data corresponding to the maximum value in the standard index data corresponding to the index data, y min And the second dimensionless data is corresponding to the minimum value in the standard index data corresponding to the index data.
In this embodiment, the abnormal location is considered to be directly based on the first dimensionless data after dimensionless index data, and more information is often required to be learned by a preset abnormal location model, so that the first similarity between the index data and the standard index data is considered, and because the first similarity is a feature after index data is mined, the abnormal location is performed based on the first similarity, so that the speed and accuracy of outputting the location result by the preset abnormal location model can be increased.
Optionally, the training process of the preset anomaly locating model may include:
acquiring a plurality of pieces of abnormal index data indicating abnormal operation states of the data link; dimensionless treatment is carried out on each piece of abnormal index data to obtain third dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to each piece of abnormal index data to obtain fourth dimensionless data; according to the third dimensionless data and the fourth dimensionless data, calculating to obtain a second similarity of each piece of abnormal index data and standard index data so as to form an abnormal positioning training sample set; training the abnormal positioning model according to the abnormal positioning training sample set to obtain a preset abnormal positioning model.
The method comprises the steps of determining an initial abnormal positioning result through a first similarity and a preset abnormal positioning model in the steps, and training based on an abnormal positioning training sample set formed by a second similarity in the process of obtaining the preset abnormal positioning model, so that on one hand, the training speed of the preset abnormal positioning model is increased, and on the other hand, the preset abnormal positioning model obtained through training can output the initial abnormal positioning result faster and more accurately.
In step 103, quality index data corresponding to the data transmitted by the data link when the data flows between the layers of the data center station is obtained.
The data center generally comprises a source pasting layer, a near source layer, a sharing layer and an analysis layer. As shown in fig. 3, the data flow diagram of the data center station can affect the state of the data link, and the quality of the data flow between the layers of the data center station transmitted by the data link. Therefore, after determining that a certain data link is abnormal, the quality index data corresponding to the data transmitted by the data link when the data flows among all layers of the data center station can be obtained, so that the abnormal type and the abnormal reason of the data link can be judged in an auxiliary mode.
The quality index data corresponding to the data transmitted by the data link when the data are transferred between the layers of the data center station can comprise data compliance of the data center station, consistency of the data when the data are transferred between the layers of the data center station, uniqueness of data table record, integrity of the data and the like.
In this embodiment, quality index data corresponding to when data transmitted by a data link flows between layers of a data center station may be obtained by comparing data quality conditions of each node of each table in the data center station. The quality index data can be obtained by comparing the data quality condition of each node of each table in the data, and the method can be used for guaranteeing the quality of multi-layer data such as a source layer, a sharing layer and an analysis layer and guaranteeing the data of the data center to effectively support business application.
In step 104, the initial positioning result of the abnormal type is rechecked according to the quality index data, and the final positioning result of the abnormal type of the data link is determined.
In this embodiment, since the quality of the data transferred by the data link flowing between the layers of the data center station also affects the state of the data link, the quality index data is used to check the initial positioning result of the abnormal type, so that the final positioning result of the abnormal type of the data link can be jointly determined based on the index data corresponding to the data link and the quality index data, and the abnormal state of the data link can be accurately monitored, thereby being beneficial to improving the data service supporting capability of the data center station and further being beneficial to the exertion of the value of the data center station.
Optionally, rechecking the initial positioning result of the abnormal type according to the quality index data, and determining the final positioning result of the abnormal type of the data link may include:
determining a first probability that the data link is of various anomaly types according to the quality index data; and determining an abnormal type final positioning result of the data link according to each first probability and the abnormal type initial positioning result.
In this embodiment, the association between the quality index data and various anomaly types of the data link is mined, so that when the quality index data takes different values, the probability that the data link is of various anomaly types can be determined, and then the final positioning result of the anomaly type of the data link is determined based on the probability that the data link is of various anomaly types and the anomaly type initial positioning result obtained in the above steps.
For example, when the determined initial positioning result of the abnormal type of a certain data link is the type a and the type B, the abnormal type with a higher probability can be selected as the final positioning result of the abnormal type of the data link based on the probabilities that the data link is the type a and the type B determined by the corresponding quality index data.
Optionally, the method for monitoring the data link state provided by the embodiment of the invention can also monitor the use state of platform hardware resources such as a CPU (central processing unit), a memory and the like of the data center platform and the use state of storage resources, and realize the resource consumption of the operation, the user and the instance by creating and managing a queue, setting the concurrent online of the CN and the queue, setting the priority and the like, thereby ensuring that the resource is reasonably utilized under the controllable condition, avoiding unordered use of the resource, preventing the performance of the database system from slowing down and stopping responding.
Optionally, the data link state monitoring method provided by the embodiment of the invention can also surround stock data resources and incremental data resources of the middle data, perform cold and hot analysis on the middle data based on a deep learning algorithm, study a temperature model based on newton's law of cooling, be used for identifying the cold and hot degree of the middle data, guide the access of later service data and the management of data quality, improve the efficiency of data access and management, and improve the accuracy and timeliness of the middle data on service application support.
Newton's law of cooling describes the law of an object transferring heat to the surrounding environment and gradually cooling when its own temperature is higher than ambient temperature. Newton's law of cooling indicates that when there is a temperature difference between the temperature of an object and the surrounding environment, the rate of change of the temperature of the object is proportional to the temperature difference between the object and the surrounding environment. The degree of cooling of a datum is constantly "cooled" over time, which is consistent with the basic meaning of newton's law of cooling, which can be applied to the process of data "cooling".
The identification method of the cold and hot degree of the data based on the temperature model is to simulate the temperature change process by exponential decay by referring to Newton's law of cooling. Regarding the data as a real object, the object with high temperature in the physical environment can be gradually cooled along with the time, and the temperature of the data in the same data storage can be gradually reduced; when the data is accessed, similar to giving new energy to the object, the temperature of the object can be increased, the data is also provided with energy by the access operation, and the temperature of the data can be increased, so that the heating of the data is realized.
Aiming at the application scene for measuring the cold and hot degree of data, the formula of Newton's law of cooling is deformed, the influence of the ambient temperature is ignored, and the variable T is increased heat Namely, the temperature rise amplitude of the data after each access can be obtained by the following formula:
T(t n ) Representing data at t n The temperature at the moment, alpha is the cooling coefficient and represents the data temperature change speed, T heat Representing the warming amplitude of the data after each access, c representing a discrete function.
The formula realizes the quantification and identification of the cold and hot degree of the data through the exact temperature value, and because the formula not only considers the influence of access on the cold and hot degree of the data, but also considers the influence of time factors on the cold and hot degree of the data, and the property of exponential operation, in the actual work load, the temperatures of any two data are different at any time point unless extremely special conditions occur, which is more beneficial to identifying the cold and hot degree of the data according to the difference of the temperature values of the data. By quantifying and visually applying the cold and hot degree of the data of the middle data platform, the multi-dimensional monitoring requirements of each level, system level and table level of the data middle data platform can be met, and the accuracy and timeliness of supporting the service application by the middle data platform are improved.
Optionally, the method for monitoring the data link state provided by the embodiment of the invention can also monitor the timeliness and the data service access condition of each business application corresponding to the data center station for acquiring the data through the data center station. By monitoring and analyzing the timeliness of each business application for acquiring data through the data center table and the update frequency of the data table, the operation and maintenance personnel can be assisted to carry out optimal configuration on the corresponding data table. By dynamically monitoring the API access times, access time length, data call success rate and the like, the method is beneficial to ensuring that each service application accurately and efficiently acquires the required data.
According to the embodiment of the invention, the index data indicating the running state of each data link is obtained through the buried point according to the type of the data link of the data center station, and different index data can be obtained for different types of data links, so that the method and the device are favorable for accurately determining whether a certain data link is abnormal or not and the initial positioning result of the abnormal type of the certain data link. On the basis, when determining that a certain data link is abnormal according to index data of each data link and a preset abnormal judgment model, acquiring an abnormal type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormal positioning model, acquiring quality index data corresponding to the data transmitted by the data link when the data are circulated among layers of the data center station, rechecking the abnormal type initial positioning result according to the quality index data, and determining an abnormal type final positioning result of the data link.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
The following are device embodiments of the invention, for details not described in detail therein, reference may be made to the corresponding method embodiments described above.
Fig. 4 is a schematic structural diagram of a data link status monitoring device according to an embodiment of the present invention, and for convenience of explanation, only a portion related to the embodiment of the present invention is shown, which is described in detail below:
as shown in fig. 4, the data link state monitoring apparatus includes: a first acquisition module 41, a processing module 42, a second acquisition module 43 and a condition monitoring module 44.
A first obtaining module 41, configured to obtain, according to a type of a data link of the data center, index data indicating an operation state of each data link through a buried point;
the processing module 42 is configured to obtain an initial positioning result of an anomaly type of the data link according to the index data corresponding to the data link and a preset anomaly positioning model when determining that the data link is anomaly according to the index data of each data link and the preset anomaly judgment model;
A second obtaining module 43, configured to obtain quality index data corresponding to when the data transmitted by the data link flows between layers of the data center station;
and the state monitoring module 44 is configured to review the initial positioning result of the abnormal type according to the quality index data, and determine a final positioning result of the abnormal type of the data link.
According to the embodiment of the invention, the index data indicating the running state of each data link is obtained through the buried point according to the type of the data link of the data center station, and different index data can be obtained for different types of data links, so that the method and the device are favorable for accurately determining whether a certain data link is abnormal or not and the initial positioning result of the abnormal type of the certain data link. On the basis, when determining that a certain data link is abnormal according to index data of each data link and a preset abnormal judgment model, acquiring an abnormal type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormal positioning model, acquiring quality index data corresponding to the data transmitted by the data link when the data are circulated among layers of the data center station, rechecking the abnormal type initial positioning result according to the quality index data, and determining an abnormal type final positioning result of the data link.
In one possible implementation, the types of data links include data links transmitted at regular time and data links transmitted in real time;
a first obtaining module 41, configured to obtain, if the type of the data link of the data center station is a data link of the timing transmission, a time interval of the data transmission, a data amount of the data transmission, and response timeliness of the data link through the buried point;
if the type of the data link of the data center station is a data link of real-time transmission, the communication state of the data link, the unblocked state of the data link, the link resource utilization rate, the network delay information, the integrity information of the data transmission and the packet loss rate are obtained through the buried point.
In one possible implementation manner, the training process of the preset abnormality judgment model includes:
acquiring normal index data indicating that the operation state of the data link is normal and abnormal index data indicating that the operation state of the data link is abnormal;
grouping the normal index data and the abnormal index data according to the source of each data link;
calculating the ratio of the number of the normal index data to the number of the abnormal index data in each group, and recording the ratio as the copy multiple of the abnormal index data in the group;
Copying the abnormal index data in each group according to the copy multiple of the abnormal index data in the group so as to form a training sample set according to all the normal index data and all the copied abnormal index data;
training the abnormality judgment model according to the training sample set to obtain a preset abnormality judgment model.
In a possible implementation manner, the processing module 42 is configured to dimensionalize the index data to obtain first dimensionless data, and dimensionalize standard index data corresponding to the index data to obtain second dimensionless data;
calculating a first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data;
and inputting the first similarity into a preset abnormal positioning model, and determining an abnormal type initial positioning result of the data link.
In one possible implementation, the processing module 42 is configured to, according toCalculating a first similarity between the index data and the standard index data;
wherein s is the first similarity between the index data and the standard index data, and y is the first similarityA dimensionless data, y max For the second dimensionless data corresponding to the maximum value in the standard index data corresponding to the index data, y min And the second dimensionless data corresponding to the minimum value in the standard index data corresponding to the index data.
In one possible implementation manner, the training process of the preset anomaly locating model includes:
acquiring a plurality of pieces of abnormal index data indicating abnormal operation states of the data link;
dimensionless treatment is carried out on each piece of abnormal index data to obtain third dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to each piece of abnormal index data to obtain fourth dimensionless data;
calculating to obtain a second similarity between each piece of abnormal index data and the standard index data according to the third dimensionless data and the fourth dimensionless data so as to form an abnormal positioning training sample set;
training the abnormal positioning model according to the abnormal positioning training sample set to obtain a preset abnormal positioning model.
In one possible implementation, the state monitoring module 44 is configured to determine, according to the quality indicator data, a first probability that the data link is of various anomaly types;
and determining an abnormal type final positioning result of the data link according to the first probability and the abnormal type initial positioning result.
Fig. 5 is a schematic diagram of a monitoring system according to an embodiment of the present invention. As shown in fig. 5, the monitoring system 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in the memory 51 and executable on the processor 50. The steps of the various data link state monitoring method embodiments described above, such as steps 101 through 104 shown in fig. 1, are implemented by processor 50 when executing computer program 52. Alternatively, the processor 50, when executing the computer program 52, performs the functions of the modules/units of the apparatus embodiments described above, such as the functions of the modules/units 41 to 44 shown in fig. 4.
By way of example, the computer program 52 may be partitioned into one or more modules/units, which are stored in the memory 51 and executed by the processor 50 to complete the present invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 52 in the monitoring system 5. For example, the computer program 52 may be split into the modules/units 41 to 44 shown in fig. 4.
The monitoring system 5 may be a computing device such as a desktop computer, a notebook computer, a palm computer, a cloud server, etc. The monitoring system 5 may include, but is not limited to, a processor 50, a memory 51. It will be appreciated by those skilled in the art that fig. 5 is merely an example of the monitoring system 5 and is not limiting of the monitoring system 5, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., the monitoring system may further include input-output devices, network access devices, buses, etc.
The processor 50 may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field-programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the monitoring system 5, such as a hard disk or a memory of the monitoring system 5. The memory 51 may also be an external storage device of the monitoring system 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the monitoring system 5. Further, the memory 51 may also include both an internal memory unit and an external memory device of the monitoring system 5. The memory 51 is used to store computer programs and other programs and data required by the monitoring system. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. 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 invention.
In the embodiments provided herein, it should be understood that the disclosed apparatus/monitoring system and method may be implemented in other ways. For example, the apparatus/monitoring system embodiments described above are merely illustrative, e.g., the division of modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present invention may implement all or part of the flow of the method of the above embodiment, or may be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the method embodiments for monitoring a data link state. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (10)
1. A method for monitoring the status of a data link, comprising:
according to the type of the data link of the data center station, index data indicating the running state of each data link is obtained through the buried point;
when determining that a certain data link is abnormal according to index data of each data link and a preset abnormality judgment model, obtaining an abnormality type initial positioning result of the data link according to the index data corresponding to the data link and the preset abnormality positioning model;
acquiring quality index data corresponding to the data transmitted by the data link when the data are transferred among all layers of the data center station;
And rechecking the initial positioning result of the abnormal type according to the quality index data, and determining the final positioning result of the abnormal type of the data link.
2. The method of claim 1, wherein the types of data links include data links transmitted at regular time and data links transmitted in real time;
the method for obtaining index data indicating the running state of each data link through the buried point according to the type of the data link of the data center station comprises the following steps:
if the type of the data link of the data center station is a data link of timing transmission, acquiring the time interval of data transmission, the data quantity of the data transmission and the response timeliness of the data link through the buried point;
if the type of the data link of the data center station is a data link of real-time transmission, the communication state of the data link, the unblocked state of the data link, the link resource utilization rate, the network delay information, the integrity information of the data transmission and the packet loss rate are obtained through the buried point.
3. The method for monitoring a data link state according to claim 1, wherein the training process of the preset anomaly determination model includes:
acquiring normal index data indicating that the operation state of the data link is normal and abnormal index data indicating that the operation state of the data link is abnormal;
Grouping the normal index data and the abnormal index data according to the source of each data link;
calculating the ratio of the number of the normal index data to the number of the abnormal index data in each group, and recording the ratio as the copy multiple of the abnormal index data in the group;
copying the abnormal index data in each group according to the copy multiple of the abnormal index data in the group so as to form a training sample set according to all the normal index data and all the copied abnormal index data;
training the abnormality judgment model according to the training sample set to obtain a preset abnormality judgment model.
4. A method for monitoring a status of a data link according to any one of claims 1 to 3, wherein the obtaining an initial positioning result of an anomaly type of the data link according to the index data corresponding to the data link and a preset anomaly positioning model includes:
dimensionless treatment is carried out on the index data to obtain first dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to the index data to obtain second dimensionless data;
calculating a first similarity between the index data and the standard index data according to the first dimensionless data and the second dimensionless data;
And inputting the first similarity into a preset abnormal positioning model, and determining an abnormal type initial positioning result of the data link.
5. The method of claim 4, wherein calculating a first similarity of the index data to the standard index data based on the first dimensionless data and the second dimensionless data comprises:
calculating a first similarity between the index data and the standard index data according to s=y;
y max -y min
wherein s is the first similarity between the index data and the standard index data, y is the first dimensionless data, y max For the second dimensionless data corresponding to the maximum value in the standard index data corresponding to the index data, y min And the second dimensionless data corresponding to the minimum value in the standard index data corresponding to the index data.
6. The method for monitoring a data link state according to claim 1, wherein the training process of the preset anomaly localization model comprises:
acquiring a plurality of pieces of abnormal index data indicating abnormal operation states of the data link;
dimensionless treatment is carried out on each piece of abnormal index data to obtain third dimensionless data, and dimensionless treatment is carried out on standard index data corresponding to each piece of abnormal index data to obtain fourth dimensionless data;
Calculating to obtain a second similarity between each piece of abnormal index data and the standard index data according to the third dimensionless data and the fourth dimensionless data so as to form an abnormal positioning training sample set;
training the abnormal positioning model according to the abnormal positioning training sample set to obtain a preset abnormal positioning model.
7. The method for monitoring the status of a data link according to claim 1, wherein the rechecking the initial positioning result of the abnormal type according to the quality index data to determine the final positioning result of the abnormal type of the data link comprises:
determining a first probability that the data link is of various anomaly types according to the quality index data;
and determining an abnormal type final positioning result of the data link according to the first probability and the abnormal type initial positioning result.
8. A data link state monitoring apparatus, comprising:
the first acquisition module is used for acquiring index data indicating the running state of each data link through the buried point according to the type of the data link of the data center station;
the processing module is used for obtaining an initial positioning result of the abnormal type of the data link according to the index data corresponding to the data link and a preset abnormal positioning model when determining that a certain data link is abnormal according to the index data of each data link and the preset abnormal judgment model;
The second acquisition module is used for acquiring quality index data corresponding to the data transmitted by the data link when the data are transferred among all layers of the data center station;
and the state monitoring module is used for rechecking the initial positioning result of the abnormal type according to the quality index data and determining the final positioning result of the abnormal type of the data link.
9. A monitoring system comprising a memory for storing a computer program and a processor for invoking and running the computer program stored in the memory to perform the method of any of claims 1 to 7.
10. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310389968.7A CN116827817A (en) | 2023-04-12 | 2023-04-12 | Data link state monitoring method, device, monitoring system and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310389968.7A CN116827817A (en) | 2023-04-12 | 2023-04-12 | Data link state monitoring method, device, monitoring system and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116827817A true CN116827817A (en) | 2023-09-29 |
Family
ID=88124835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310389968.7A Pending CN116827817A (en) | 2023-04-12 | 2023-04-12 | Data link state monitoring method, device, monitoring system and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116827817A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102164051A (en) * | 2011-05-18 | 2011-08-24 | 西安交通大学 | Service-oriented fault detection and positioning method |
| CN103199919A (en) * | 2013-04-19 | 2013-07-10 | 重庆邮电大学 | Multi-parameter-sensed high-accuracy network fault screening and positioning system and method |
| JP2014092799A (en) * | 2012-10-31 | 2014-05-19 | Sumitomo Heavy Ind Ltd | Abnormality cause specifying system |
| CN105391579A (en) * | 2015-11-25 | 2016-03-09 | 国家电网公司 | Electric power communication network fault positioning method based on key alarm sets and supervised classification |
| CN111679158A (en) * | 2020-08-04 | 2020-09-18 | 国网内蒙古东部电力有限公司呼伦贝尔供电公司 | Power distribution network fault identification method based on synchronous measurement data similarity |
| CN112187514A (en) * | 2020-09-02 | 2021-01-05 | 上海御威通信科技有限公司 | Intelligent operation and maintenance system, method and terminal for data center network equipment |
| CN112966957A (en) * | 2021-03-22 | 2021-06-15 | 国家电网有限公司大数据中心 | Data link abnormity positioning method and device, electronic equipment and storage medium |
| CN113242443A (en) * | 2021-05-28 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Data stream transmission abnormity detection method and device |
| CN113473514A (en) * | 2021-09-06 | 2021-10-01 | 国网江苏省电力有限公司信息通信分公司 | Electric power wireless private network fault diagnosis model training method, diagnosis method and apparatus |
| CN115209452A (en) * | 2021-04-09 | 2022-10-18 | 中国移动通信集团江苏有限公司 | Core network hidden danger checking method and device, electronic equipment and storage medium |
| CN115269870A (en) * | 2022-07-26 | 2022-11-01 | 国网天津市电力公司 | Method for realizing classification and early warning of data link faults in data based on knowledge graph |
| CN115758200A (en) * | 2022-09-28 | 2023-03-07 | 航天智控(北京)监测技术有限公司 | Vibration signal fault identification method and system based on similarity measurement |
-
2023
- 2023-04-12 CN CN202310389968.7A patent/CN116827817A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102164051A (en) * | 2011-05-18 | 2011-08-24 | 西安交通大学 | Service-oriented fault detection and positioning method |
| JP2014092799A (en) * | 2012-10-31 | 2014-05-19 | Sumitomo Heavy Ind Ltd | Abnormality cause specifying system |
| CN103199919A (en) * | 2013-04-19 | 2013-07-10 | 重庆邮电大学 | Multi-parameter-sensed high-accuracy network fault screening and positioning system and method |
| CN105391579A (en) * | 2015-11-25 | 2016-03-09 | 国家电网公司 | Electric power communication network fault positioning method based on key alarm sets and supervised classification |
| CN111679158A (en) * | 2020-08-04 | 2020-09-18 | 国网内蒙古东部电力有限公司呼伦贝尔供电公司 | Power distribution network fault identification method based on synchronous measurement data similarity |
| CN112187514A (en) * | 2020-09-02 | 2021-01-05 | 上海御威通信科技有限公司 | Intelligent operation and maintenance system, method and terminal for data center network equipment |
| CN112966957A (en) * | 2021-03-22 | 2021-06-15 | 国家电网有限公司大数据中心 | Data link abnormity positioning method and device, electronic equipment and storage medium |
| CN115209452A (en) * | 2021-04-09 | 2022-10-18 | 中国移动通信集团江苏有限公司 | Core network hidden danger checking method and device, electronic equipment and storage medium |
| CN113242443A (en) * | 2021-05-28 | 2021-08-10 | 北京达佳互联信息技术有限公司 | Data stream transmission abnormity detection method and device |
| CN113473514A (en) * | 2021-09-06 | 2021-10-01 | 国网江苏省电力有限公司信息通信分公司 | Electric power wireless private network fault diagnosis model training method, diagnosis method and apparatus |
| CN115269870A (en) * | 2022-07-26 | 2022-11-01 | 国网天津市电力公司 | Method for realizing classification and early warning of data link faults in data based on knowledge graph |
| CN115758200A (en) * | 2022-09-28 | 2023-03-07 | 航天智控(北京)监测技术有限公司 | Vibration signal fault identification method and system based on similarity measurement |
Non-Patent Citations (1)
| Title |
|---|
| 剡振业: "基于数据中台的数据链路监测及综合评价模型的研究", 《中国优秀硕士学位论文全文数据库（电子期刊）（工程科技II辑）》, vol. 2023, no. 3, 15 March 2023 (2023-03-15), pages 042 - 1125 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103748579B (en) | Data are handled in MapReduce frame | |
| EP3567496B1 (en) | Systems and methods for indexing and searching | |
| CN111190792B (en) | Log storage method and device, electronic equipment and readable storage medium | |
| CN111400288A (en) | Data quality inspection method and system | |
| CN102169491B (en) | Dynamic detection method for multi-data concentrated and repeated records | |
| CN110201393A (en) | Configuration data storage method and device and electronic equipment | |
| CN112100219B (en) | Report generation method, device, equipment and medium based on database query processing | |
| CN113327136A (en) | Attribution analysis method and device, electronic equipment and storage medium | |
| CN111414410A (en) | Data processing method, device, equipment and storage medium | |
| CN105868956A (en) | Data processing method and device | |
| CN114612194A (en) | Product recommendation method and device, electronic equipment and storage medium | |
| CN110675238A (en) | Client label configuration method, system, readable storage medium and electronic equipment | |
| CN112288604A (en) | Judicial case data processing method and device, electronic equipment and readable storage medium | |
| CN114429265A (en) | Enterprise portrait service construction method, device and equipment based on grid technology | |
| CN112699142A (en) | Cold and hot data processing method and device, electronic equipment and storage medium | |
| CN109542657A (en) | The processing method and server of system exception | |
| CN110471912B (en) | Employee attribute information verification method and device and terminal equipment | |
| CN116827817A (en) | Data link state monitoring method, device, monitoring system and storage medium | |
| JP5497925B2 (en) | Content management apparatus, content management method and program | |
| CN114116811B (en) | Log processing method, device, equipment and storage medium | |
| CN115481026A (en) | Test case generation method and device, computer equipment and storage medium | |
| Ruan et al. | Evaluating performance variations cross cloud data centres using multiview comparative workload traces analysis | |
| CN109828970B (en) | Information processing method and device and electronic equipment | |
| CN113158497A (en) | Online service experiment method and device, computer equipment and storage medium | |
| US20140164397A1 (en) | Apparatus and method for searching information |
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 |