CN113923096A - Network element fault early warning method and device, electronic equipment and storage medium - Google Patents
Network element fault early warning method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113923096A CN113923096A CN202010575127.1A CN202010575127A CN113923096A CN 113923096 A CN113923096 A CN 113923096A CN 202010575127 A CN202010575127 A CN 202010575127A CN 113923096 A CN113923096 A CN 113923096A
- Authority
- CN
- China
- Prior art keywords
- service data
- network element
- target
- historical
- general service
- 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.)
- Granted
Links
Images
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- H04L41/0604—Management of faults, events, alarms or notifications using filtering, e.g. reduction of information by using priority, element types, position or time
-
- 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
-
- 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
- H04L41/0681—Configuration of triggering conditions
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Maintenance And Management Of Digital Transmission (AREA)
- Telephonic Communication Services (AREA)
Abstract
The embodiment of the invention provides a network element fault early warning method, a network element fault early warning device, electronic equipment and a storage medium, wherein target general service data of a target network element is obtained according to a preset strategy; acquiring historical general service data of a target network element from historical service data of the target network element, wherein the historical service data comprises at least one type of service data; according to the method, the target general service data is subjected to early warning analysis according to the historical general service data to obtain an early warning result, and the target general service data and the historical general service data are used in the early warning analysis of the network element fault, so that the network element fault is not required to be analyzed independently for the network elements of different manufacturers, the use efficiency of the network element data is improved, the automatic early warning of the network element fault is realized, and the timeliness and the accuracy of the network fault early warning are improved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a network element fault early warning method and apparatus, an electronic device, and a storage medium.
Background
With the development of network technology and the high-speed growth of mobile network users, the role played by the core network of a telecommunication service operator becomes more and more important, and the timely and reasonable maintenance work of the core network is the key for ensuring that the core network of the operator can provide high-quality telecommunication service.
In core network maintenance, discovery of network failures generally depends on network management alarms and user complaints. The network management alarm is generally generated and reported by each network element, and then is analyzed and judged by an engineer to obtain a fault diagnosis conclusion, and meanwhile, a fault positioning means depends on the engineer to perform comprehensive analysis and judgment according to the alarm information, the communication network element configuration information, the signaling and other information to finally position a fault point.
Then, with the fact that core network networks are more and more complex, network element types are more and more, network element alarm information of different manufacturers is inconsistent, manual analysis is difficult to achieve, and a network fault is often found only after a user complaint occurs, so that the problems of lagging network fault early warning, poor timeliness and low accuracy exist in the prior art.
Disclosure of Invention
The invention provides a network element fault early warning method, a network element fault early warning device, electronic equipment and a storage medium, which are used for solving the problems of network fault early warning lag, poor timeliness and low accuracy.
According to a first aspect of the embodiments of the present disclosure, the present disclosure provides a network element fault early warning method, where the method includes:
acquiring target general service data of a target network element according to a preset strategy;
acquiring historical general service data of the target network element from historical service data of the target network element, wherein the historical service data comprises at least one type of service data;
and performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
Optionally, performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result, where the early warning analysis includes:
processing and analyzing the target general service data according to the historical general service data to obtain an early warning result, wherein the processing and analyzing comprises at least one of the following steps: threshold analysis, mutation analysis, and bias analysis.
Optionally, the performing threshold analysis on the target general service data according to the historical general service data to obtain an early warning result includes:
determining a threshold range according to the historical universal service data;
and determining an early warning result according to whether the threshold value of the general service data is in the threshold value range.
Optionally, the determining a threshold range according to the historical general service data includes:
acquiring target historical data which accords with preset conditions in the historical general service data;
performing machine learning based on an fbprophet algorithm by using the target historical data, and predicting general service data predicted in a second preset time in the future;
and determining a threshold range according to the threshold of the predicted general service data.
Optionally, the performing mutation analysis on the target general service data according to the historical general service data to determine an early warning result includes:
acquiring one or more target historical data corresponding to the target general service data in historical general service data;
calculating the change rate of the general service data relative to the target historical data;
and determining an early warning result according to the change rate.
Optionally, the performing deviation analysis on the target general service data according to the historical general service data to determine an early warning result includes:
determining a target traffic volume ratio corresponding to the target network element according to the target general service data;
acquiring historical traffic volume ratio corresponding to the target network element according to the historical universal service data;
calculating a deviation value of the target traffic volume ratio and the historical traffic volume ratio;
and determining an early warning result according to the deviation value.
Optionally, the target general service data includes an online user number and/or flow data; the acquiring of the target general service data of the target network element according to the preset strategy comprises:
acquiring the network element type of the target network element;
determining a general service item corresponding to the network element type according to a preset mapping relation, wherein the mapping relation is the mapping relation between the network element type and the general service item;
and acquiring the number of online users and/or flow data corresponding to the universal service item of the target network element at preset time intervals.
According to a second aspect of the embodiments of the present disclosure, the present disclosure provides a network element fault early warning apparatus, including:
the first acquisition module is used for acquiring target general service data of a target network element according to a preset strategy;
a second obtaining module, configured to obtain historical general service data of the target network element from historical service data of the target network element, where the historical service data includes at least one type of service data;
and the analysis module is used for carrying out early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
Optionally, the analysis module is specifically configured to:
processing and analyzing the target general service data according to the historical general service data to obtain an early warning result, wherein the processing and analyzing comprises at least one of the following steps: threshold analysis, mutation analysis, and bias analysis.
Optionally, the analysis module is configured to perform threshold analysis on the target general service data according to the historical general service data, and when an early warning result is obtained, specifically:
determining a threshold range according to the historical universal service data;
and determining an early warning result according to whether the threshold value of the general service data is in the threshold value range.
Optionally, when determining the threshold range according to the historical general service data, the analysis module is specifically configured to:
acquiring target historical data which accords with preset conditions in the historical general service data;
performing machine learning based on an fbprophet algorithm by using the target historical data, and predicting general service data predicted in a second preset time in the future;
and determining a threshold range according to the threshold of the predicted general service data.
Optionally, the analysis module is configured to perform mutation analysis on the target general service data according to the historical general service data, and when an early warning result is determined, specifically configured to:
acquiring one or more target historical data corresponding to the target general service data in historical general service data;
calculating the change rate of the general service data relative to the target historical data;
and determining an early warning result according to the change rate.
Optionally, the analysis module is specifically configured to, when performing deviation analysis on the target general service data according to the historical general service data and determining an early warning result:
determining a target traffic volume ratio corresponding to the target network element according to the target general service data;
acquiring historical traffic volume ratio corresponding to the target network element according to the historical universal service data;
calculating a deviation value of the target traffic volume ratio and the historical traffic volume ratio;
and determining an early warning result according to the deviation value.
Optionally, the target general service data includes an online user number and/or flow data; the first obtaining module is specifically configured to:
acquiring the network element type of the target network element;
determining a general service item corresponding to the network element type according to a preset mapping relation, wherein the mapping relation is the mapping relation between the network element type and the general service item;
and acquiring the number of online users and/or flow data corresponding to the universal service item of the target network element at preset time intervals.
According to a third aspect of the embodiments of the present disclosure, the present invention provides an electronic apparatus including: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to perform the network element fault pre-warning method according to any one of the first aspect of the embodiments of the disclosure.
According to a fourth aspect of the embodiments of the present disclosure, the present disclosure provides a computer-readable storage medium, in which computer-executable instructions are stored, and when the computer-executable instructions are executed by a processor, the computer-readable storage medium is configured to implement the network element fault early warning method according to any one of the first aspect of the embodiments of the present disclosure.
According to the network element fault early warning method, the network element fault early warning device, the electronic equipment and the storage medium, the target general service data of the target network element is obtained according to the preset strategy; acquiring historical general service data of the target network element from historical service data of the target network element, wherein the historical service data comprises at least one type of service data; and performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result, wherein the target general service data and the historical general service data are used in the early warning analysis on the network element fault, so that the network element fault early warning method does not need to perform independent analysis on network elements of different manufacturers, improves the use efficiency of the network element data, realizes automatic early warning of the network element fault, and improves the timeliness and the accuracy of network fault early warning.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 is an application scenario diagram of a network element fault early warning method according to an embodiment of the present invention;
fig. 2 is a flowchart of a network element fault early warning method according to an embodiment of the present invention;
fig. 3 is a flowchart of a network element fault early warning method according to another embodiment of the present invention;
FIG. 4 is a flowchart of step S204 in the embodiment shown in FIG. 3;
FIG. 5 is a flowchart of step S205 in the embodiment shown in FIG. 3;
FIG. 6 is a flowchart of step S206 in the embodiment shown in FIG. 3;
fig. 7 is a schematic structural diagram of a network element fault early warning apparatus according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
With the foregoing drawings in mind, certain embodiments of the disclosure have been shown and described in more detail below. These drawings and written description are not intended to limit the scope of the disclosed concepts in any way, but rather to illustrate the concepts of the disclosure to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The terms to which the present invention relates will be explained first:
network element: the network element is the minimum unit monitored and managed in network management, and the definition of the network element can be different according to different network architectures. For example, the Network element may include a base station, and may also include a Mobility Management Entity (MME), a Serving GateWay (SGW), a Public Data Network (PDN), and so on, and for the Network element in the core Network, different Network elements carry different services and services.
Fig. 1 is an application scenario diagram of a network element fault early warning method according to an embodiment of the present invention, as shown in fig. 1, the network element fault early warning method according to this embodiment is applied to an electronic device, for example, a network management device 11, the network management device 11 is connected to a core network, the core network includes a plurality of network elements 12 for core switching or call routing functions, different network elements 12 carry different functions, and further play a role in supporting different telecommunication network services, the network management device 11 may obtain alarm information uploaded by the network elements 12 through the core network, and simultaneously, send the network element alarm information to a terminal device 13 used by an operation and maintenance worker according to needs.
In the prior art, in the process of maintaining a core network, network fault discovery generally depends on network management alarms and user complaints. The network management alarm is generally generated and reported by each network element, the timeliness is good, the fault problem can be reflected at the first time, and the user complaint is often caused by the condition that the user use is influenced for a long time because the serious problem occurs in the network, so the timeliness is poor.
However, in the way of implementing the fault early warning by network management alarm, after the network element reports information, an engineer comprehensively analyzes and judges the information such as alarm information, communication network element configuration information, signaling and the like, and finally locates a fault point. With the complexity of the core network, the variety of network elements is more and more, the alarm information of the network elements of different manufacturers is inconsistent, engineers need to be familiar with the network elements of all manufacturers to realize accurate identification and early warning of network faults, and the method has the advantages of high operation difficulty and low accuracy. Therefore, the network fault is often discovered only after the user complaints, and the problems of network fault early warning lag, poor timeliness and low accuracy are caused.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 2 is a flowchart of a network element fault early warning method according to an embodiment of the present invention, and as shown in fig. 2, the network element fault early warning method according to the embodiment includes the following steps:
step S101, obtaining target general service data of a target network element according to a preset strategy.
The target network element refers to a network element to be subjected to early warning, and the target network element may be one network element or a group of network elements realizing the same or similar functions. There are various methods for determining a target network element, for example, actively maintaining the network element according to a preset maintenance plan, and taking the network element to be maintained in the maintenance plan as the target network element; or after passively receiving the request information of the network element, taking the network element sending the request information as the network element to be pre-warned, which may be designed according to specific requirements and usage scenarios, and is not limited herein.
The target universal service data refers to the universal service data of the target network element. The general service data refers to service data generated by a network element during a process of carrying traffic or service. For network elements produced by different manufacturers, the general service data is used for representing the basic operation state of the network elements, so that the unified early warning of the network elements of different manufacturers can be realized according to the general service data, early warning strategies do not need to be configured separately for different manufacturers, and the early warning efficiency is effectively improved. The implementation manner of the general service data may be various, for example, the amount of online users, the flow rate, and the like, and the specific content of the general service data may be set according to the usage scenario and the requirement, that is, determined according to a preset policy, which is not specifically limited herein.
Step S102, historical general service data of the target network element is obtained from historical service data of the target network element, wherein the historical service data comprises at least one type of service data.
The historical service data refers to service data that the network element has generated and stored in a specific storage medium in the past period of time. The historical traffic data may characterize the operational characteristics of the network element over a historical period of time, and for the same or a class of network elements, there is a certain correlation between the historical traffic data and the current traffic data. However, as the time of the historical data is longer, the correlation between the historical data and the current operation state of the gateway is gradually weakened, so that the time corresponding to the historical data is not easy to be too long. The historical data may be selected from data in the past year, and it should be noted that, for different network elements and different usage scenarios, the time length corresponding to the historical data may be different and may be determined as needed.
Specifically, the historical general service data refers to historical service data of general service data, and the historical service data includes at least one type of service data, for example, general service data and non-general service data, and the non-general service data is specific service data generated by network elements of various manufacturers.
And S103, performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
For the same or same type of network element, namely the target network element, because a certain correlation exists between the historical general service data and the current target general service data, when the historical general service data is inconsistent with the target general service data, the operation state of the network element corresponding to the historical general service data is explained, and the operation state of the network element corresponding to the target general service data is inconsistent, namely the operation state of the network element is changed, so that the current operation state of the gateway can be judged according to the relationship between the historical general service data and the target service data, and the early warning of the operation state of the network element is realized.
In the embodiment, target general service data of a target network element is obtained according to a preset strategy; acquiring historical general service data of a target network element from historical service data of the target network element, wherein the historical service data comprises at least one type of service data; according to the method, the target general service data is subjected to early warning analysis according to the historical general service data to obtain an early warning result, and the target general service data and the historical general service data are used in the early warning analysis of the network element fault, so that the network element fault is not required to be analyzed independently for the network elements of different manufacturers, the use efficiency of the network element data is improved, the automatic early warning of the network element fault is realized, and the timeliness and the accuracy of the network fault early warning are improved.
Fig. 3 is a flowchart of a network element fault early warning method according to another embodiment of the present invention, and as shown in fig. 3, the network element fault early warning method according to this embodiment further refines steps S101 and S103 on the basis of the network element fault early warning method according to the embodiment shown in fig. 2, where target general service data includes an online user number and/or traffic data, and the network element fault early warning method according to this embodiment includes the following steps:
step S201, a network element type of the target network element is obtained.
Specifically, according to the role played by the target network element, the network elements may be divided into different network element types, for example, a mobility management node, a service gateway, a public data network, and the like, and for different types of network elements, the services and services carried by the network elements are different, and the corresponding operating status features are also different.
Step S202, determining a general service item corresponding to the network element type according to a preset mapping relationship, wherein the mapping relationship is the mapping relationship between the network element type and the general service item.
For different network element types, the common service items are different, for example, the common service item corresponding to the type a network element is call connection, the common service item corresponding to the type B network element is mobility management, and the mapping policies of the different network elements corresponding to the different common service items are determined by the preset mapping relationship, that is, the common service items corresponding to the different network elements can be determined according to the preset mapping relationship.
Step S203, acquiring the number of online users and/or flow data corresponding to the universal service item of the target network element at intervals of a preset time length.
Specifically, the data acquisition frequency is set at intervals of a preset time length, for example, the preset time length is 5 minutes, that is, data of the target network element is acquired every 5 minutes; the preset time length is 1 hour, that is, the data of the target network element is collected every 1 hour, and the specific numerical value of the preset time length can be determined according to different requirements, which is not specifically limited herein.
When the target network element undertakes the service corresponding to the universal service item, service information, such as the number of online users and flow data, is generated. The data belongs to basic data, and the basic data can be generated by network elements generated by different manufacturers. The online user number and/or the flow data are/is used as target general service data, the operation state of a target network element can be well reflected, unified early warning on network elements of different manufacturers can be realized, and early warning accuracy and early warning efficiency are improved.
And step S204, performing threshold analysis on the target general service data according to the historical general service data, and determining an early warning result.
When the historical general service data of the target network element and the specific threshold value of the target general service data change, the early warning result of the target network element can be obtained by analyzing the change.
Optionally, as shown in fig. 4, step S204 includes two specific implementation steps S2041 and S2042:
step S2041, according to the historical general service data, a threshold range is determined.
Specifically, the threshold range may be a value interval where all the historical general service data are located, for example, a maximum value and a minimum value interval, and more specifically, for example, a maximum value and a minimum value of the historical traffic of the target network element. The threshold range may be a numerical interval in which part of the historical general service data is located, for example, an effective value interval of the historical general service data within a 95% confidence interval, and the determination method of the threshold range is various and may be determined according to specific needs, which is not specifically limited herein.
Optionally, determining the threshold range according to the historical general service data includes:
and acquiring target historical data which accords with preset conditions in the historical general service data. Specifically, the method comprises the steps of screening historical general service data, removing deviation points, screening data capable of obviously representing the operating state characteristics, and acting on sample data, namely target historical data.
And performing machine learning based on the fbprophet algorithm by using the target historical data, and predicting the predicted general service data in a second preset time length in the future. Prediction of data within a second preset time period, for example, 1 week or 10 days, can be achieved by performing fbprophet algorithm-based machine learning with the target historical data as sample data.
And determining a threshold range according to the threshold of the predicted general service data.
And determining a threshold range by taking the predicted general service data output by machine learning as a standard. Because the predicted general service data output by machine learning contains trend change rules compared with historical general service data, the threshold range determined according to the threshold of the predicted general service data is closer to the real numerical range of data generated by the target network element in normal operation, and the accuracy of fault early warning on the target network element can be improved.
Step S2042, according to whether the threshold value of the general service data is in the threshold value range, determining an early warning result.
The general service data is processed according to the same calculation method as that for calculating the historical general service data, and the threshold value of the general service data can be obtained. And judging whether the threshold falls into a threshold range or not, judging whether the general service data is normal or not, and further judging whether the running state of the target network element corresponding to the general service data is normal or not, and judging whether the running state of the target network element is normal or not, wherein the judgment result is an early warning result.
For example, according to the historical general service data, the effective value interval of the historical general service data in the 95% confidence interval of the target network element is determined to be [100,120], wherein the historical general service data is the flow data. Correspondingly, according to the same calculation method, namely calculating the effective value of the general service data in the 95% confidence interval to obtain the threshold value of the general service data as 110, and if the threshold value is not beyond the range of the threshold value, judging that the data is normal, namely the running state of the target network element is normal; correspondingly, the threshold value of the obtained general service data is 130, and if the obtained general service data exceeds the threshold value range, the data is judged to be abnormal, namely the running state of the target network element is abnormal.
Of course, it is also possible to add a fluctuation correction value on the basis of the threshold range, for example, the fluctuation correction value is 5, that is, the threshold falls within the range of [100,120] ± 5, and the operation state of the target network element is considered to be normal, so as to increase the stability of the algorithm and reduce the probability of false alarm.
And S205, performing mutation analysis on the target general service data according to the historical general service data, and determining an early warning result.
Specifically, the sudden change refers to a sudden change of the service data, and for the network element, the service data which changes suddenly cannot be generated when the network element operates in a normal state, so that the fault early warning of the target network element can be realized by performing the sudden change analysis on the target general service data.
Optionally, as shown in fig. 5, step S205 includes three specific implementation steps S2051, S2052, and S2053:
step S2051, one or more target historical data corresponding to the target general service data in the historical general service data are acquired.
And acquiring target historical data which accords with preset conditions in the historical general service data. Specifically, the method comprises the steps of screening historical general service data, removing deviation points, screening data capable of obviously representing the operating state characteristics, and acting on sample data, namely target historical data.
Step S2052 calculates a change rate of the general service data with respect to the target history data.
With the operation of the service carried by the network element, the target historical data generated by the network element may generate a certain change, including a rising, falling or fluctuating change within a certain range, and the change rate represents the degree of the fluctuating change. From the extent of the change, the rate of change of the change can be determined.
Specifically, the rate of change may be based on different units, such as, for example, a rate of change per minute, a rate of change per 15 minutes, a rate of change per hour, a rate of change per day, and the like. The unit of the change rate can be determined according to different requirements, and is not particularly limited herein. The rate of change may be implemented as an absolute value, for example, the rate of change of the online user amount is: 1000 persons/day, i.e. daily fluctuations of the online user volume are within 1000 persons. The rate of change may also be implemented as a relative value, for example, the rate of change of the online user amount is 1%, i.e., the daily fluctuation of the online user amount is within 1%.
Illustratively, a method of calculating a rate of change includes:
suppose the index of the general service data is x1Index of target historical data is x2The calculation formula of the change rate d is d ═ x1-x2) /x2, further, when d is larger than the preset value d0And if so, the network element index is abnormal.
And step S2053, determining an early warning result according to the change rate.
When the target network element operates normally, the fluctuation situation of the target general service data generated by the target network element should be similar to the fluctuation situation of the target historical data, for example, the daily online user number and the change rate in the target general service data and the target historical data are all maintained within 1%, which indicates that the target network element operates normally. When the change rate of the daily online user number in the target general service data is 10%, it may be caused by a connection failure of the target network element, and thus it may be determined that the target network element has a failure.
In the step of this embodiment, the state of the target network element is determined according to the change rate of the service data relative to the target historical data, so that the state change condition of the target network element can be better represented, the accurate change degree of the target network element can be determined according to the change condition, and the accuracy of fault early warning is improved.
And step S206, performing deviation analysis on the target general service data according to the historical general service data, and determining an early warning result.
Specifically, the deviation analysis is to analyze the deviation of the ratio of the traffic volume carried by the target network element according to the target general service data. For example, for a normally operating network element, the traffic carried by the network element accounts for a fixed percentage of the network element group in which the network element is located, for example, 10%. Therefore, by distributing the traffic in a balanced manner, the pressure can be shared among different network elements, and the service processing efficiency is improved. When a network element in the network element group has a problem, the traffic borne by the network element is reduced, and the fault condition of the target network element can be judged according to the deviation of the network element.
Optionally, as shown in fig. 6, step S206 includes four specific implementation steps S2061, S2062, S2063, and S2064:
step S2061, determining a target traffic volume ratio corresponding to the target network element according to the target general service data.
Specifically, the target general service data includes characterization information of the data quantity value, and the target data quantity value corresponding to the target general service data can be determined according to the characterization information. By calculating the ratio of the target data quantity value to the preset total quantity value, the target traffic volume ratio corresponding to the target network element can be determined. For example, the traffic of the information forwarding service corresponding to the target network element accounts for 10%, that is, the target network element bears 10% of the traffic.
Step S2062, obtaining the historical service volume ratio corresponding to the target network element according to the historical general service data.
Similarly, according to the historical general service data of the target network element, the historical service volume ratio corresponding to the target network element can be determined by calculating the ratio of the historical data quantity value to the historical total quantity value. Wherein, the historical traffic volume ratio and the corresponding general service item of the historical traffic volume ratio should be the same.
In step S2063, a deviation value between the target traffic volume ratio and the historical traffic volume ratio is calculated.
Calculating the difference between the target traffic volume ratio and the historical traffic volume ratio to obtain a signed deviation value, wherein when the deviation value is a positive value, the target traffic volume ratio is increased, and when the deviation value is a negative value, the target traffic volume ratio is decreased. For example, if the target traffic proportion is 10% and the historical traffic proportion is 8%, the deviation value is 2%, which indicates that the target traffic proportion is increased by 2%.
And S2064, determining an early warning result according to the deviation value.
When the deviation value of the target traffic volume ratio is greater than the preset deviation threshold, it may be determined that the target network element is in an abnormal state.
Illustratively, a method of bias analysis includes:
for a group of target network elements for load sharing, according to a preset proportion and a preset deviation degree, assuming that n target network elements exist, and the indexes are x respectively1、x2……xnThe proportion of the traffic of each network element is set as a1、a2……anWherein the index of the network element i is xiWith a traffic ratio of aiIf the preset deviation ratio threshold is d, then
And the network element index is abnormal.
In this embodiment, the operation state of the target network element is determined according to the deviation value of the target traffic ratio, so that the accuracy of determining the operation state of the target network element can be further increased, and the application scenario and the use flexibility of the method of this embodiment are increased.
It should be noted that, in this embodiment, the step of processing and analyzing the target general service data according to the historical general service data corresponding to the steps S204, S205, and S206 to obtain the early warning result may use any one of the methods in the steps S204, S205, and S206 separately as needed to obtain the early warning result; the multiple methods in S204, S205, and S206 may also be used in different orders, and the early warning result may be obtained in multiple ways according to multiple results obtained correspondingly, for example, the early warning result may be determined according to the multiple results and the weight coefficients corresponding to the multiple results; for another example, the early warning result is determined according to the most deteriorated result in the multiple results. As specifically defined herein.
Optionally, after any one of steps S204, S205, and S206, the method further includes:
and step S207, pushing the early warning result to the terminal equipment.
In order to enable a maintainer to determine a failed network element at the first time after a network fails, the electronic device applying the network element failure early warning method provided by the embodiment pushes an early warning result to a terminal device used by an operation and maintenance worker, for example, the electronic device is pushed to a mobile phone of the operation and maintenance worker in a mode of WeChat, APP and the like, so that the operation and maintenance worker can locate the network element failure in time, and the timeliness of network element failure early warning is improved.
Fig. 7 is a schematic structural diagram of a network element fault early warning apparatus according to an embodiment of the present invention, and as shown in fig. 7, the network element fault early warning apparatus 7 according to the embodiment includes:
a first obtaining module 71, configured to obtain target general service data of a target network element according to a preset policy;
a second obtaining module 72, configured to obtain historical general service data of the target network element from historical service data of the target network element, where the historical service data includes at least one type of service data;
and the analysis module 73 is used for performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
The first obtaining module 71, the second obtaining module 72 and the analyzing module 73 are connected in sequence. The network element fault early warning apparatus 7 provided in this embodiment may execute the technical solution of the method embodiment shown in any one of fig. 2 to 6, and the implementation principle and the technical effect are similar, and are not described herein again.
Fig. 8 is a schematic diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 8, the electronic device according to the embodiment includes: a memory 81, a processor 82 and a computer program.
The computer program is stored in the memory 81 and configured to be executed by the processor 82 to implement the network element fault early warning apparatus provided in any one of the embodiments corresponding to fig. 2 to fig. 6 of the present invention.
The memory 81 and the processor 82 are connected by a bus 83.
The relevant descriptions and effects corresponding to the steps in the embodiments corresponding to fig. 2 to fig. 6 can be understood, and are not described in detail herein.
An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to implement the network element fault early warning apparatus provided in any embodiment of the present invention corresponding to fig. 2 to fig. 6.
The computer readable storage medium may be, among others, ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of modules is merely a division of logical functions, and an actual implementation may have another division, for example, a plurality of modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.
It will be understood that the invention is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the invention is limited only by the appended claims.
Claims (10)
1. A network element fault early warning method is characterized by comprising the following steps:
acquiring target general service data of a target network element according to a preset strategy;
acquiring historical general service data of the target network element from historical service data of the target network element, wherein the historical service data comprises at least one type of service data;
and performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
2. The method of claim 1, wherein performing early warning analysis on the target general service data according to the historical general service data to obtain an early warning result comprises:
processing and analyzing the target general service data according to the historical general service data to obtain an early warning result, wherein the processing and analyzing comprises at least one of the following steps: threshold analysis, mutation analysis, and bias analysis.
3. The method according to claim 2, wherein the performing threshold analysis on the target general service data according to the historical general service data to obtain an early warning result comprises:
determining a threshold range according to the historical universal service data;
and determining an early warning result according to whether the threshold value of the general service data is in the threshold value range.
4. The method of claim 3, wherein determining a threshold range from the historical universal traffic data comprises:
acquiring target historical data which accords with preset conditions in the historical general service data;
performing machine learning based on an fbprophet algorithm by using the target historical data, and predicting general service data predicted in a second preset time in the future;
and determining a threshold range according to the threshold of the predicted general service data.
5. The method according to claim 3, wherein the performing mutation analysis on the target general service data according to the historical general service data to determine an early warning result comprises:
acquiring one or more target historical data corresponding to the target general service data in historical general service data;
calculating the change rate of the general service data relative to the target historical data;
and determining an early warning result according to the change rate.
6. The method according to claim 3, wherein the performing deviation analysis on the target general service data according to the historical general service data to determine an early warning result comprises:
determining a target traffic volume ratio corresponding to the target network element according to the target general service data;
acquiring historical traffic volume ratio corresponding to the target network element according to the historical universal service data;
calculating a deviation value of the target traffic volume ratio and the historical traffic volume ratio;
and determining an early warning result according to the deviation value.
7. The method according to any of claims 1-6, wherein the target universal service data comprises the number of online users, and/or traffic data; the acquiring of the target general service data of the target network element according to the preset strategy comprises:
acquiring the network element type of the target network element;
determining a general service item corresponding to the network element type according to a preset mapping relation, wherein the mapping relation is the mapping relation between the network element type and the general service item;
and acquiring the number of online users and/or flow data corresponding to the universal service item of the target network element at preset time intervals.
8. A network element fault early warning apparatus, the apparatus comprising:
the first acquisition module is used for acquiring target general service data of a target network element according to a preset strategy;
a second obtaining module, configured to obtain historical general service data of the target network element from historical service data of the target network element, where the historical service data includes at least one type of service data;
and the analysis module is used for carrying out early warning analysis on the target general service data according to the historical general service data to obtain an early warning result.
9. An electronic device, comprising: a memory, a processor, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the network element fault pre-warning method of any one of claims 1-7.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the computer-executable instructions are configured to implement the network element fault warning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010575127.1A CN113923096B (en) | 2020-06-22 | 2020-06-22 | Network element fault early warning method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010575127.1A CN113923096B (en) | 2020-06-22 | 2020-06-22 | Network element fault early warning method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113923096A true CN113923096A (en) | 2022-01-11 |
| CN113923096B CN113923096B (en) | 2023-05-30 |
Family
ID=79231225
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010575127.1A Active CN113923096B (en) | 2020-06-22 | 2020-06-22 | Network element fault early warning method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113923096B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116389223A (en) * | 2023-04-26 | 2023-07-04 | 福芯高照(上海)科技有限公司 | Artificial intelligence visual early warning system and method based on big data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2001017169A2 (en) * | 1999-08-31 | 2001-03-08 | Accenture Llp | A system, method and article of manufacture for a network-based predictive fault management system |
| US6405250B1 (en) * | 1999-01-25 | 2002-06-11 | Lucent Technologies Inc. | Network management system based on passive monitoring and proactive management for formulation behavior state transition models |
| CN105786493A (en) * | 2016-02-24 | 2016-07-20 | 山东超越数控电子有限公司 | Operation and maintenance system collecting and configuring method |
| CN109921955A (en) * | 2017-12-12 | 2019-06-21 | 北京嘀嘀无限科技发展有限公司 | Portfolio monitoring method, system, computer equipment and storage medium |
| CN109995592A (en) * | 2019-04-09 | 2019-07-09 | 中国联合网络通信集团有限公司 | Quality of service monitoring method and equipment |
| CN110658905A (en) * | 2019-09-23 | 2020-01-07 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment running state |
| CN110990433A (en) * | 2019-11-21 | 2020-04-10 | 深圳马可孛罗科技有限公司 | Real-time service monitoring and early warning method and early warning device |
| CN111132179A (en) * | 2019-12-26 | 2020-05-08 | 宜通世纪物联网研究院(广州)有限公司 | Cell scheduling method, system, device and storage medium |
-
2020
- 2020-06-22 CN CN202010575127.1A patent/CN113923096B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6405250B1 (en) * | 1999-01-25 | 2002-06-11 | Lucent Technologies Inc. | Network management system based on passive monitoring and proactive management for formulation behavior state transition models |
| WO2001017169A2 (en) * | 1999-08-31 | 2001-03-08 | Accenture Llp | A system, method and article of manufacture for a network-based predictive fault management system |
| CN105786493A (en) * | 2016-02-24 | 2016-07-20 | 山东超越数控电子有限公司 | Operation and maintenance system collecting and configuring method |
| CN109921955A (en) * | 2017-12-12 | 2019-06-21 | 北京嘀嘀无限科技发展有限公司 | Portfolio monitoring method, system, computer equipment and storage medium |
| CN109995592A (en) * | 2019-04-09 | 2019-07-09 | 中国联合网络通信集团有限公司 | Quality of service monitoring method and equipment |
| CN110658905A (en) * | 2019-09-23 | 2020-01-07 | 珠海格力电器股份有限公司 | Early warning method, early warning system and early warning device for equipment running state |
| CN110990433A (en) * | 2019-11-21 | 2020-04-10 | 深圳马可孛罗科技有限公司 | Real-time service monitoring and early warning method and early warning device |
| CN111132179A (en) * | 2019-12-26 | 2020-05-08 | 宜通世纪物联网研究院(广州)有限公司 | Cell scheduling method, system, device and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| H BHATNAGAR ET AL.: "Network Design and Performance Evaluation of an Early Warning Network", IEEE * |
| 陈龙;万明;李世锋;: "基于大数据的电网信息运维主动监控预警系统", 电气应用 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116389223A (en) * | 2023-04-26 | 2023-07-04 | 福芯高照(上海)科技有限公司 | Artificial intelligence visual early warning system and method based on big data |
| CN116389223B (en) * | 2023-04-26 | 2023-12-22 | 郑州数智科技集团有限公司 | Artificial intelligence visual early warning system and method based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113923096B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jin et al. | Nevermind, the problem is already fixed: proactively detecting and troubleshooting customer dsl problems | |
| CN107026746B (en) | Network service quality evaluation method, system and network equipment | |
| CN107204894B (en) | Method and device for monitoring network service quality | |
| JPH08307524A (en) | Method and equipment for discriminating risk in abnormal conditions of constitutional element of communication network | |
| CN101288275A (en) | Method and apparatus for providing end-to-end high quality services based on performance characterizations of network conditions | |
| CN111400295B (en) | Power distribution network power failure event analysis method and device and storage medium | |
| CN107947968B (en) | Method and device for processing network quality complaint information | |
| CN110891283A (en) | Small base station monitoring device and method based on edge calculation model | |
| CN102447577A (en) | Alarming treatment method of communication network for client orientation | |
| CN109379757B (en) | Single-user fault diagnosis method and device based on narrowband Internet of things service | |
| CN114205226B (en) | Method and system for guaranteeing business application experience | |
| CN108696371B (en) | Network fault determination method and system | |
| CN113923096B (en) | Network element fault early warning method and device, electronic equipment and storage medium | |
| CN109963292B (en) | Complaint prediction method, complaint prediction device, electronic apparatus, and storage medium | |
| CN115334560B (en) | Base station abnormality monitoring method, device, equipment and computer readable storage medium | |
| CN109788501B (en) | 2G +4G mobile network voice quality joint evaluation method and device | |
| CN114138750B (en) | AI consultation database based cluster building method and system | |
| JP7173273B2 (en) | Failure analysis device, failure analysis method and failure analysis program | |
| US20080192915A1 (en) | Method for Routing Network Call and Network Call Center | |
| CN112101698B (en) | Electric power communication optical cable operation capability assessment method | |
| CN113891336A (en) | Communication network frequency-reducing network-quitting method and device, computer equipment and storage medium | |
| CN114567907B (en) | Resource management method, device and system of cross-domain network | |
| CN115633390B (en) | IAB base station-based mobile network access regulation and control method and system | |
| WO2022121513A1 (en) | Method and apparatus for generating worst value of performance index, and electronic device and storage medium | |
| CN115545637A (en) | Alarm work order dispatching method, device, equipment and storage 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |