CN115334560A - Method, device and equipment for monitoring base station abnormity and computer readable storage medium - Google Patents
Method, device and equipment for monitoring base station abnormity and computer readable storage medium Download PDFInfo
- Publication number
- CN115334560A CN115334560A CN202211001605.3A CN202211001605A CN115334560A CN 115334560 A CN115334560 A CN 115334560A CN 202211001605 A CN202211001605 A CN 202211001605A CN 115334560 A CN115334560 A CN 115334560A
- Authority
- CN
- China
- Prior art keywords
- base station
- monitored
- historical
- data
- traffic
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 230000005856 abnormality Effects 0.000 claims abstract description 25
- 238000012549 training Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 24
- 230000015654 memory Effects 0.000 claims description 13
- 238000012806 monitoring device Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 abstract description 14
- 230000002159 abnormal effect Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 5
- 235000019580 granularity Nutrition 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010801 machine learning Methods 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
- 238000003062 neural network model Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W16/00—Network planning, e.g. coverage or traffic planning tools; Network deployment, e.g. resource partitioning or cells structures
- H04W16/22—Traffic simulation tools or models
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
- Telephonic Communication Services (AREA)
Abstract
The application provides a method, a device and equipment for monitoring base station abnormity and a computer readable storage medium. The method comprises the following steps: acquiring predicted flow data of a base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period; determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states within a preset time period and historical flow data of the base station to be monitored in historical busy and idle states; and if the flow weight is greater than a preset weight threshold, determining that the base station to be monitored is in invisible abnormality. According to the method, the flow weight is determined by acquiring the predicted flow data and the historical flow data when the traffic is idle and busy; whether the base station to be monitored is in invisible abnormity is determined through the flow weight, and the problem of low efficiency of abnormity detection of the base station in the prior art is solved.
Description
Technical Field
The present application relates to communications technologies, and in particular, to a method, an apparatus, a device, and a computer-readable storage medium for monitoring base station anomalies.
Background
With the development of network technology and the increasing expansion of network scale, the network topology and network devices become more and more complex, and the types of services carried by the network devices also increase gradually. These all lead to a greatly increased chance of failure or performance problems in the network and network monitoring faces even greater challenges. The purpose of network monitoring is to discover abnormal conditions in the network in time by continuously monitoring network equipment and network operation conditions, and to send out an alarm notification in time when an abnormality occurs in the network, so as to remind network management personnel to take necessary measures to keep the network operating normally.
Currently, there are two types of abnormal detection based on a flow base station: one is for anomaly detection of network traffic surges and the other is for anomaly detection of network traffic drops to zero.
However, when the base station flow suddenly drops in a certain period of time and is lower than the flow value in the normal state, the flow is larger than zero flow at the moment, and the flow is restored to the normal state in a later period of time; when the traffic of the base station suddenly increases in a certain period of time, the traffic of the user is normal in a certain period of time, but there is a potential abnormality, and the existing technology cannot detect such network abnormality, so that the efficiency of detecting the abnormality of the existing base station is low.
Disclosure of Invention
The application provides a base station abnormity monitoring method, a base station abnormity monitoring device, base station abnormity monitoring equipment and a computer readable storage medium, which are used for solving the problem of low base station abnormity detection efficiency in the prior art.
An embodiment of the present application provides a method for monitoring base station anomalies, where the method includes:
acquiring predicted flow data of a base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period;
determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period;
and responding to the fact that the flow weight is larger than a preset weight threshold value, and determining that the base station to be monitored is in invisible abnormity.
In an embodiment, acquiring predicted traffic data of a base station to be monitored when the base station is busy in a preset time period specifically includes:
predicting historical flow data of a base station to be monitored by using a trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy and idle in a preset time period;
wherein, the trained traffic prediction model is obtained by using the coverage scene of the base station and the traffic data training.
In an embodiment, before predicting historical traffic data of a base station to be monitored by using a trained traffic prediction model to obtain predicted traffic data of the base station to be monitored when the base station to be monitored is busy within a preset time period, the method further includes:
acquiring a coverage scene of a base station and service data of the base station at each moment, and dividing busy and idle time according to the service data of the base station at each moment to acquire time characteristics of the base station; wherein the traffic data comprises total traffic data;
and taking the coverage scene and the time characteristics of the base station as training samples, taking total flow data of the base station at each moment as label data of the training samples, and training a flow prediction model by using the training samples and the label data to obtain a trained flow prediction model.
In an embodiment, the obtaining the time characteristics of the base stations according to busy-idle time division of the service data of each base station at each time specifically includes:
when the total flow data of the base station in a certain period is the maximum total flow data in the total period, determining that the period is busy; when the total flow data of the base station in a certain time period is the minimum total flow data in the total time period, determining that the time period is idle;
or
The service data also comprises user access number, and when the user access number of the base station in a certain period is the maximum user access number in the total period, the period is determined to be busy; and when the user access number of the base station in a certain period is the minimum user access number in the total period, determining that the period is idle.
In an embodiment, determining a traffic weight of a base station to be monitored according to predicted traffic data of the base station to be monitored during busy and idle periods within a preset time period and historical traffic data of the base station to be monitored during historical busy and idle periods includes:
acquiring a first traffic weight according to predicted traffic data of a base station to be monitored during busy hours in a preset time period and historical traffic data of the base station to be monitored during historical busy hours;
acquiring a second traffic weight according to the idle predicted traffic data and the historical idle traffic data of the base station to be monitored in a preset time period;
and processing the first flow weight and the second flow weight to obtain the flow weight of the base station to be monitored.
In an embodiment, obtaining a first traffic weight according to predicted traffic data of a base station to be monitored during busy hours within a preset time period and historical traffic data during historical busy hours includes:
calculating and obtaining a first flow weight according to a first formula, wherein the first formula specifically comprises:
wherein, ω is 1 Is a first traffic weight, A pre The traffic flow data of the base station to be monitored in busy hours in a preset time period are represented, min (A) is minimum historical traffic flow data of the base station to be monitored in historical busy hours, and max (A) is maximum historical traffic flow data of the base station to be monitored in historical busy hours;
obtaining a second traffic weight according to the predicted traffic data of the base station to be monitored in idle time within the preset time period and the historical traffic data in historical idle time, and specifically comprising the following steps:
and calculating to obtain a second flow weight according to a second formula, wherein the second formula specifically comprises:
wherein, ω is 2 Is a second flow weight, B pre The traffic data of the base station to be monitored in idle in a preset time period is represented, min (B) is minimum historical traffic data of the base station to be monitored in historical idle, and max (B) is maximum historical traffic data of the base station to be monitored in historical idle.
In an embodiment, the processing the first traffic weight and the second traffic weight to obtain the traffic weight of the base station to be monitored specifically includes:
calculating and obtaining the flow weight of the base station to be monitored according to a third formula, wherein the third formula specifically comprises the following steps:
ω=αω 1 +βω 2
omega is the traffic weight of the base station to be monitored, alpha is the ratio coefficient of the first traffic weight, and beta is the ratio coefficient of the second traffic weight.
Another embodiment of the present application provides a device for monitoring base station abnormalities, including:
the acquisition module is used for acquiring the predicted flow data of the base station to be monitored in busy and idle time within a preset time period and the historical flow data of the base station to be monitored in historical busy and idle time;
the processing module is used for determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle time within a preset time period and historical flow data of the base station to be monitored in historical busy and idle time;
the processing module is further used for determining that the base station to be monitored has the invisible abnormality in response to the fact that the flow weight is larger than the preset weight threshold.
Another embodiment of the present application provides a monitoring device, including: a memory and a processor;
the memory stores computer execution instructions;
the processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1 to 7.
Yet another embodiment of the application provides a computer-readable storage medium having stored thereon computer-executable instructions for implementing the method of any one of claims 1 to 7 when executed by a processor.
Yet another embodiment of the application provides a computer program product comprising a computer program which, when executed by a processor, performs the method of any one of claims 1 to 7.
According to the base station abnormity monitoring method, device and equipment and the computer readable storage medium, predicted flow data of a base station to be monitored in busy and idle states in a preset time period and historical flow data of the base station to be monitored in historical busy and idle states are obtained; determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states within a preset time period and historical flow data of the base station to be monitored in historical busy and idle states; and if the flow weight is larger than a preset weight threshold value, determining that the base station to be monitored is in invisible abnormity. Determining the traffic weight by acquiring predicted traffic data and historical traffic data in idle and busy hours; whether the base station to be monitored is in invisible abnormity is determined through the flow weight, and the problem of low efficiency of abnormity detection of the base station in the prior art is solved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of a method for monitoring base station anomalies according to an embodiment of the present application;
fig. 2 is a flowchart of a method for monitoring base station abnormality according to another embodiment of the present application;
fig. 3 is a flowchart of a method for monitoring base station anomalies according to yet another embodiment of the present application;
fig. 4 is a flowchart of a method for determining traffic weight of a base station to be monitored according to another embodiment of the present application;
fig. 5 is a schematic structural diagram of a base station anomaly monitoring device according to yet another embodiment of the present application;
fig. 6 is a schematic structural diagram of a monitoring device according to another embodiment of the present application.
With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts 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 embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
With the development of network technology and the increasing scale of networks, the network topology and network devices become more and more complex, and the types of services carried by the network devices also increase gradually. These all result in a greatly increased chance of failure or performance problems in the network, and network monitoring faces greater challenges. The purpose of network monitoring is to discover abnormal conditions in the network in time by continuously monitoring network equipment and network operation conditions, and to send out an alarm notification in time when an abnormality occurs in the network, so as to remind network management personnel to take necessary measures to keep the network operating normally.
Currently, there are two types of abnormal detection based on a flow base station: one is anomaly detection for network traffic surges and the other is anomaly detection for network traffic drops to zero.
However, when the base station flow suddenly drops in a certain period of time and is lower than the flow value in the normal state, the flow is larger than zero flow at the moment, and the flow is restored to the normal state in a later period of time; when the traffic of the base station suddenly increases in a certain period of time, the traffic of the user is normal in a certain period of time, but there is a potential abnormality, and the existing technology cannot detect such network abnormality, so that the efficiency of detecting the abnormality of the existing base station is low.
In view of the foregoing problems, embodiments of the present application provide a method, an apparatus, a device and a computer-readable storage medium for monitoring base station anomalies, which aim to solve the problem of low base station anomaly detection efficiency in the prior art. The technical idea of the application is as follows: acquiring predicted flow data of a base station to be monitored in busy and idle time within a preset time period and historical flow data of the base station to be monitored in historical busy and idle time; determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period; and if the flow weight is greater than a preset weight threshold, determining that the base station to be monitored is in invisible abnormality. According to the method, the flow weight is determined by acquiring the predicted flow data and the historical flow data in idle and busy hours; whether the base station to be monitored is invisible and abnormal is determined through the flow weight, and the problem of low efficiency of abnormal detection of the base station in the prior art is solved.
As shown in fig. 1, an embodiment of the present application provides a method for monitoring base station anomalies, where the method includes the following steps:
s101, acquiring predicted flow data of a base station to be monitored in busy and idle states within a preset time period and historical flow data of the base station to be monitored in historical busy and idle states.
In this step, the busy/idle time is determined according to the size of the traffic data in a time period corresponding to one whole day from the operation of the base station.
Illustratively, the predicted flow data of the base station to be monitored during busy and idle time within the preset time period can be obtained through a trained base station flow prediction model and a long-short term memory neural network model.
For example, historical traffic data of a base station to be monitored during historical busy hours may be obtained through a corresponding base station control platform and an OSSIM OPEN SOURCE SECURITY INFORMATION MANAGEMENT system (OPEN SOURCE SECURITY INFORMATION MANAGEMENT) platform.
It can be understood that the acquisition of the predicted traffic data when the base station to be monitored is busy or idle in the preset time period and the acquisition of the historical traffic data when the base station to be monitored is historically busy or idle are not limited to those described in the foregoing embodiments, and other acquisition manners may also be used according to actual conditions, which is not limited in this embodiment.
S102, determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle time within the preset time period and the historical flow data of the base station to be monitored in historical busy and idle time.
In the step, according to the idle predicted flow data and the minimum historical idle flow data of the base station to be monitored in the preset time period, the difference value between the idle predicted flow data and the minimum historical idle flow data in the preset time period is obtained; and obtaining the difference value of the maximum traffic data in idle time and the minimum traffic data in historical idle time according to the maximum traffic data in historical idle time and the minimum traffic data in historical idle time of the base station to be monitored. And the two differences are calculated.
Acquiring the difference value between the predicted flow data of the busy hour in the preset time period and the minimum flow data of the historical busy hour according to the predicted flow data of the busy hour in the preset time period and the minimum flow data of the historical busy hour of the base station to be monitored; and obtaining the difference value of the maximum flow data in busy hours and the minimum flow data in historical busy hours according to the maximum flow data in historical busy hours and the minimum flow data in historical busy hours of the base station to be monitored. And the two differences are calculated.
And respectively carrying out certain weight assignment on the difference value operation results of the idle time and the busy time so as to determine the flow weight of the base station to be monitored.
It can be understood that, certain weight assignment may be performed on the difference operation result in the idle time and the busy time respectively, and the assignment may be performed according to an actual working condition, which is not limited in this embodiment.
And S103, if the flow weight is larger than a preset weight threshold value.
In this step, the preset weight threshold is a value preset in advance according to the condition of the base station, the preset traffic weight threshold is a traffic weight standard value set by an operator according to the coverage scene, the threshold values of different coverage scenes are different in size, and after the traffic weight is obtained in the above step, it is determined whether the traffic weight is greater than the preset weight threshold value.
It is understood that the preset weight threshold may be assigned according to an actual operating condition, and the embodiment is not limited thereto.
And S104, determining that the base station to be monitored has invisible abnormality.
In the step, the invisible abnormity is not the fault of the base station in the traditional sense, the invisible abnormity in the invention is the phenomenon that the base station actually runs out of the normal running range, and the phenomenon is defined as the invisible abnormity phenomenon of the base station.
And determining that the base station to be monitored has invisible abnormality by judging that the flow weight is greater than a preset weight threshold value.
In the technical scheme, the method comprises the steps of acquiring predicted flow data of a base station to be monitored in busy and idle states within a preset time period and historical flow data of the base station to be monitored in historical busy and idle states; determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period; and if the flow weight is greater than a preset weight threshold, determining that the base station to be monitored is in invisible abnormality. According to the method, the flow weight is determined by acquiring the predicted flow data and the historical flow data when the traffic is idle and busy; whether the base station to be monitored is invisible and abnormal is determined through the flow weight, and the problem of low efficiency of abnormal detection of the base station in the prior art is solved. Therefore, the abnormity is optimized in a targeted manner, and the network perception of the user is actively improved.
As shown in fig. 2, another embodiment of the present application provides a method for monitoring base station anomalies, where the method includes the following steps:
s201, predicting historical flow data of a base station to be monitored by using a trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy in a preset time period; wherein, the trained traffic prediction model is obtained by using the coverage scene of the base station and the traffic data training.
In this step, the coverage scene type is the area scene where the access user under the base station is located, and the coverage scene corresponding to the base station is further determined according to the area scene. Exemplary, regional scenes include, but are not limited to: residential areas, business office areas, industrial parks, urban villages, commercial shopping areas, transportation hubs, urban arterial roads, schools and the like. When the number of residential areas in which access users under the base station are located is large, it can be determined that the coverage scene of the base station is the residential area.
The traffic data is service traffic usage data recorded in the operation process of the base station, and the data can be divided into minute data, hour data and day data according to different corresponding time granularities. Illustratively, the historical traffic data of the base station is the minute-level traffic data of the base station cell, and the traffic unit is MB.
And training the time series model by using the coverage scene of the base station and the traffic data so as to obtain a traffic prediction model. And predicting historical flow data of the base station to be monitored by using the trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy and idle in a preset time period.
S202, determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle time within the preset time period and the historical flow data of the base station to be monitored in historical busy and idle time.
This step is already detailed in S102, and is not described herein again.
And S203, if the flow weight is greater than a preset weight threshold value.
This step is already detailed in S103, and is not described herein again.
And S204, determining that the base station to be monitored has invisible abnormality.
This step is already described in detail in S104, and is not described herein again.
In the technical scheme, historical flow data of the base station to be monitored is predicted by using a trained flow prediction model, and predicted flow data of the base station to be monitored in busy and idle time within a preset time period is obtained; the trained traffic prediction model is obtained by using a coverage scene of a base station and traffic data training; determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period; and if the flow weight is larger than a preset weight threshold value, determining that the base station to be monitored is in invisible abnormity. Determining the flow weight by establishing a prediction model and acquiring predicted flow data and historical flow data in idle and busy hours; whether the base station to be monitored is invisible and abnormal is determined through the flow weight, and the problem of low efficiency of abnormal detection of the base station in the prior art is solved.
As shown in fig. 3, a method for monitoring base station abnormality according to another embodiment of the present application includes the following steps:
s301, acquiring a coverage scene of a base station and service data of the base station at each moment, and dividing busy and idle time according to the service data of the base station at each moment to acquire time characteristics of the base station; wherein the traffic data comprises total traffic data.
In the step, all base stations in a certain period area are obtained through a control platform, and infrastructure data and service data of all the base stations are obtained; wherein the traffic data comprises total traffic data. The infrastructure data is determined engineering parameter data of the base station in the planning and construction process, and also comprises data such as engineering parameter adjustment and the like of the base station in the operation and maintenance process. The traffic data is service traffic usage data recorded in the operation process of the base station, and the data can be divided into minute data, hour data and day data according to different corresponding time granularities.
Illustratively, the infrastructure data of the base station cell is base station height, longitude and latitude, azimuth, downward inclination, cell identifier, frequency band, bandwidth, belonging grid and the like, the historical traffic data of the base station is the minute-level traffic data of the base station cell, and the traffic unit is MB.
And according to the coverage characteristics in the base station infrastructure data, acquiring a specific coverage scene of the base station. Exemplary, regional scenes include, but are not limited to: residential areas, business office areas, industrial parks, urban villages, commercial shopping areas, transportation hubs, urban arterial roads, schools and the like. When the number of residential areas in which access users under the base station are located is large, it can be determined that the coverage scene of the base station is the residential area.
And dividing the time period of the flow data into working days, weekends and holidays according to the flow data of the base station. Furthermore, working days, weekends and holidays are divided into idle time and busy time based on the time dimension, so that the time characteristics of the base station are obtained.
For example, workdays, weekends and holidays can be distinguished according to the date attribute of the base station, and idle and busy hours can be divided according to the idle and busy hour attribute of the base station. For example, 18 hours-24 hours of a certain workday in a certain area are workday busy hours, and 0 hours-18 hours of a certain workday in a certain area are workday busy hours.
It can be understood that the coverage scenario of the base station and the acquisition of the service data of the base station at each time are not limited to those described in the foregoing embodiments, and may also be other acquisition manners according to actual working conditions, which is not limited in this embodiment.
In a specific embodiment, the obtaining the time characteristics of the base stations according to the busy/idle time division performed by each base station on the service data at each time includes:
s301a, when the total flow data of the base station in a certain period is the maximum total flow data in the total period, determining that the period is busy; and when the total flow data of the base station in a certain time period is the minimum total flow data in the total time period, determining that the time period is idle.
In this step, according to the hour granularity traffic data of the base station, the hour with the maximum traffic is selected as the busy hour of the base station, and the hour with the minimum traffic is selected as the idle hour of the base station.
In another specific embodiment, the obtaining the time characteristics of the base stations according to busy-idle time division performed by the service data of each base station at each time may further include:
s301b, the service data also comprises user access numbers, and when the user access number of the base station in a certain period is the maximum user access number in the total period, the period is determined to be busy; and when the user access number of the base station in a certain period is the minimum user access number in the total period, determining that the period is idle.
In this step, the determination of the base station idle and busy hours may also select the hour with the most user connections as the busy hour and the hour with the least user connections as the idle hour according to the number of user connections in the base station hour granularity.
S302, taking the coverage scene and the time characteristics of the base station as training samples, taking total flow data of the base station at each moment as label data of the training samples, and training a flow prediction model by using the training samples and the label data to obtain a trained flow prediction model.
In this step, after the coverage scenario and the time characteristic of the base station are obtained in step S301, a base station traffic prediction model based on a time series is established by using traffic data corresponding to the coverage scenario and the time characteristic of the base station as a training sample and using a total traffic of each hour of the history of the base station as a training sample label, where the time series model is a supervised algorithm generally applicable in the field of machine learning at present. According to the historical small-granularity real flow data of the base station, the historical flow data of the base station to be monitored is predicted through a flow prediction model, and the predicted flow data of the base station to be monitored in busy and idle time within a preset time period is obtained.
Illustratively, the time series model may select an LSTM (Long Short-Term Memory) model, the scene type and the traffic of each time of the base station are input into the units of the model according to the time series characteristics, and the traffic use condition of each base station in the next time period is finally obtained through the extraction of the time series data characteristics and the fusion of the Memory information by each unit.
It should be understood that the time series model is not limited to the above-described embodiment, and may be other models according to actual requirements, and the embodiment is not limited thereto.
S303, predicting historical flow data of the base station to be monitored by using the trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy in a preset time period; wherein, the trained traffic prediction model is obtained by using the coverage scene of the base station and the traffic data training.
This step is already detailed in S201, and is not described herein again.
S304, determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle time within the preset time period and the historical flow data of the base station to be monitored in historical busy and idle time.
This step is already detailed in S102, and is not described herein again.
And S305, if the flow weight is greater than a preset weight threshold value.
This step is already described in detail in S103, and is not described herein again.
S306, determining that the base station to be monitored is invisible and abnormal.
This step is already described in detail in S104, and is not described herein again.
In the technical scheme, a coverage scene of the base station and service data of the base station at each moment are obtained, and when the total traffic data of the base station at a certain time interval is the maximum total traffic data in the total time interval, the time interval is determined to be busy; when the total traffic data of the base station in a certain time period is the minimum total traffic data in the total time period, determining that the time period is idle, and obtaining the time characteristic of the base station; or, the service data further includes a user access number, and when the user access number of the base station in a certain period is the maximum user access number in the total period, the period is determined to be busy; and when the user access number of the base station in a certain period is the minimum user access number in the total period, determining that the period is idle. And then taking the coverage scene and the time characteristics of the base station as training samples, taking the total flow data of the base station at each moment as label data of the training samples, and training a flow prediction model by using the training samples and the label data to obtain a trained flow prediction model. Predicting historical flow data of a base station to be monitored by using a trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy or idle within a preset time period; further determining the flow weight of the base station to be monitored; and if the flow weight is larger than a preset weight threshold value, automatically identifying that the stealthy abnormality occurs in the base station to be monitored. The problem of low efficiency of base station anomaly detection in the prior art is solved, so that the anomaly is optimized in a targeted manner, and the network perception of a user is actively improved.
As shown in fig. 4, a method for determining traffic weight of a base station to be monitored according to another embodiment of the present application includes the following steps:
s401, according to the predicted flow data of the base station to be monitored in busy hours in a preset time period and historical flow data of the base station to be monitored in historical busy hours, a first flow weight is obtained.
In this step, a first flow weight is calculated and obtained according to a first formula, where the first formula specifically includes:
wherein, ω is 1 Is a first traffic weight, A pre The traffic flow data of the base station to be monitored in busy time at that time is represented, min (A) the minimum historical traffic flow data of the base station to be monitored in historical busy time, and max (A) the maximum historical traffic flow data of the base station to be monitored in historical busy time
S402, obtaining a second flow weight according to the idle predicted flow data and the historical flow data of the base station to be monitored in the preset time period.
In this step, a second flow weight is calculated according to a second formula, where the second formula specifically includes:
wherein, ω is 2 Is a second traffic weight, B pre The traffic data of the base station to be monitored in the current idle state is represented, min (B) minimum historical traffic data of the base station to be monitored in the historical idle state is represented, and max (B) maximum historical traffic data of the base station to be monitored in the historical idle state is represented.
And S403, processing the first flow weight and the second flow weight to obtain the flow weight of the base station to be monitored.
In this step, the traffic weight of the base station to be monitored is calculated and obtained according to a third formula, where the third formula specifically includes:
ω=αω 1 +βω 2
omega is the traffic weight of the base station to be monitored, alpha is the ratio coefficient of the first traffic weight, and beta is the ratio coefficient of the second traffic weight.
It is understood that α and β are set according to actual conditions, and the embodiment is not limited thereto.
As shown in fig. 5, a base station abnormality monitoring apparatus 500 according to another embodiment of the present application includes:
an obtaining module 501, configured to obtain predicted traffic data of a base station to be monitored during busy and idle periods within a preset time period and historical traffic data of the base station to be monitored during historical busy and idle periods;
a processing module 502, configured to determine a traffic weight of a base station to be monitored according to predicted traffic data of the base station to be monitored during busy and idle periods within a preset time period and historical traffic data of the base station to be monitored during historical busy and idle periods;
the processing module 502 is further configured to determine that the stealthy anomaly occurs in the base station to be monitored if the traffic weight is greater than the preset weight threshold.
In an embodiment, acquiring predicted traffic data of a to-be-monitored base station when the to-be-monitored base station is busy in a preset time period specifically includes:
the processing module 502 is further configured to predict historical traffic data of the base station to be monitored by using the trained traffic prediction model, and obtain predicted traffic data of the base station to be monitored when the base station to be monitored is busy within a preset time period;
wherein, the trained traffic prediction model is obtained by using the coverage scene of the base station and the traffic data training.
In an embodiment, before predicting historical traffic data of a base station to be monitored by using a trained traffic prediction model to obtain predicted traffic data of the base station to be monitored when the base station to be monitored is busy within a preset time period, the method further includes:
the processing module 502 is further configured to obtain a coverage scenario of the base station and service data of the base station at each time, and perform busy-time division according to the service data of the base station at each time to obtain a time characteristic of the base station; wherein the service data comprises total traffic data;
the processing module 502 is further configured to use the coverage scene and the time characteristic of the base station as training samples, use total traffic data of the base station at each time as label data of the training samples, train a traffic prediction model using the training samples and the label data, and obtain a trained traffic prediction model.
In an embodiment, the obtaining the time characteristics of the base stations according to the busy/idle time division of the service data of each base station at each time includes:
the processing module 502 is further configured to determine that a time interval is busy when total traffic data of the base station in a certain time interval is maximum total traffic data in the total time interval; when the total flow data of the base station in a certain time period is the minimum total flow data in the total time period, determining that the time period is idle;
or alternatively
The processing module 502 is further configured to use the service data to further include a user access number, and when the user access number of the base station in a certain period is the maximum user access number in the total period, determine that the period is busy; and when the user access number of the base station in a certain period is the minimum user access number in the total period, determining that the period is idle.
In an embodiment, determining a traffic weight of a base station to be monitored according to predicted traffic data of the base station to be monitored during busy and idle periods within a preset time period and historical traffic data of the base station to be monitored during historical busy and idle periods specifically includes:
the processing module 502 is further configured to obtain a first traffic weight according to predicted traffic data of the base station to be monitored during busy hours within a preset time period and historical traffic data of the base station to be monitored during historical busy hours;
the processing module 502 is further configured to obtain a second traffic weight according to predicted traffic data of the base station to be monitored during idle in a preset time period and historical traffic data of the base station to be monitored during historical idle;
the processing module 502 is further configured to process the first traffic weight and the second traffic weight to obtain a traffic weight of the base station to be monitored.
In an embodiment, obtaining a first traffic weight according to predicted traffic data of a base station to be monitored during busy hours within a preset time period and historical traffic data during historical busy hours includes:
the processing module 502 is further configured to calculate and obtain a first traffic weight according to a first formula, where the first formula specifically includes:
wherein, ω is 1 Is a first traffic weight, A pre The traffic flow prediction method comprises the steps of representing predicted traffic flow data of a base station to be monitored in busy time at that time, min (A) minimum historical traffic flow data of the base station to be monitored in historical busy time, and max (A) maximum historical traffic flow data of the base station to be monitored in historical busy time;
the processing module 502 is further configured to obtain a second traffic weight according to the predicted traffic data of the to-be-monitored base station in idle time within the preset time period and the historical traffic data in historical idle time, and specifically includes:
the processing module 502 is further configured to calculate and obtain a second flow weight according to a second formula, where the second formula specifically includes:
wherein, ω is 2 Is a second flow weight, B pre The traffic data of the base station to be monitored in the current idle state is represented, min (B) minimum historical traffic data of the base station to be monitored in the historical idle state is represented, and max (B) maximum historical traffic data of the base station to be monitored in the historical idle state is represented.
In an embodiment, the processing the first traffic weight and the second traffic weight to obtain the traffic weight of the base station to be monitored specifically includes:
the processing module 502 is further configured to calculate and obtain a traffic weight of the base station to be monitored according to a third formula, where the third formula specifically includes:
ω=αω 1 +βω 2
omega is the traffic weight of the base station to be monitored, alpha is the ratio coefficient of the first traffic weight, and beta is the ratio coefficient of the second traffic weight.
As shown in fig. 6, another embodiment of the present application provides a monitoring device 600, where the monitoring device 600 includes a memory 601 and a processor 602.
Wherein the memory 601 is used for storing computer instructions executable by the processor;
the processor 602, when executing computer instructions, performs the steps of the methods in the embodiments described above. Reference may be made in particular to the description relating to the method embodiments described above.
Alternatively, the memory 601 may be separate or integrated with the processor 602. When the memory 601 is separately provided, the electronic device further includes a bus for connecting the memory 601 and the processor 602.
The embodiment of the present application further provides a computer-readable storage medium, in which computer instructions are stored, and when the processor executes the computer instructions, the steps in the method in the foregoing embodiment are implemented.
Embodiments of the present application further provide a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the computer instructions implement the steps of the method in the above embodiments.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application 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 application being indicated by the following claims.
It will be understood that the present application 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 application is limited only by the appended claims.
Claims (10)
1. A method for monitoring base station abnormity is characterized in that the method comprises the following steps:
acquiring predicted flow data of a base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period;
determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle states and historical flow data of the base station to be monitored in historical busy and idle states within a preset time period;
and responding to the fact that the flow weight is larger than a preset weight threshold value, and determining that the base station to be monitored is in invisible abnormity.
2. The monitoring method according to claim 1, wherein the obtaining of predicted traffic data of the base station to be monitored during busy/idle time within a preset time period specifically comprises:
predicting historical flow data of a base station to be monitored by using a trained flow prediction model to obtain predicted flow data of the base station to be monitored when the base station to be monitored is busy and idle within a preset time period;
wherein the trained traffic prediction model is obtained by using the coverage scene of the base station and traffic data training.
3. The monitoring method according to claim 2, wherein before predicting historical traffic data of a base station to be monitored by using the trained traffic prediction model to obtain predicted traffic data of the base station to be monitored when the base station to be monitored is busy or idle within a preset time period, the method further comprises:
acquiring a coverage scene of a base station and service data of the base station at each moment, and dividing busy and idle time according to the service data of the base station at each moment to acquire time characteristics of the base station; wherein the traffic data comprises total traffic data;
and taking the coverage scene and the time characteristic of the base station as training samples, taking total flow data of the base station at each moment as label data of the training samples, and training a flow prediction model by using the training samples and the label data to obtain the trained flow prediction model.
4. The method for monitoring base station abnormalities according to claim 3, wherein the time characteristics of the base stations are obtained by dividing busy/idle time according to the service data of each base station at each time, and specifically comprises:
when the total flow data of the base station in a certain period is the maximum total flow data in the total period, determining that the period is busy; when the total flow data of the base station in a certain time period is the minimum total flow data in the total time period, determining that the time period is idle;
or
The service data also comprises user access number, and when the user access number of the base station in a certain period is the maximum user access number in the total period, the period is determined to be busy; and when the user access number of the base station in a certain period is the minimum user access number in the total period, determining that the period is idle.
5. The method according to any one of claims 1 to 4, wherein the determining the traffic weight of the base station to be monitored according to predicted traffic data of the base station to be monitored during busy/idle time within a preset time period and historical traffic data during historical busy/idle time specifically comprises:
acquiring a first traffic weight according to predicted traffic data of the base station to be monitored during busy hours in a preset time period and historical traffic data of the base station to be monitored during historical busy hours;
acquiring a second flow weight according to the idle predicted flow data and the historical idle flow data of the base station to be monitored in a preset time period;
and processing the first flow weight and the second flow weight to obtain the flow weight of the base station to be monitored.
6. The method for monitoring base station abnormalities according to claim 5, wherein obtaining a first traffic weight according to predicted traffic data of the base station to be monitored during busy hours within a preset time period and historical traffic data during historical busy hours specifically comprises:
calculating and obtaining the first flow weight according to a first formula, wherein the first formula specifically comprises:
wherein, ω is 1 Is the first traffic weight, A pre The traffic monitoring method comprises the steps of representing predicted traffic data of a base station to be monitored in busy hours within a preset time period, min (A) minimum historical traffic data of the base station to be monitored in historical busy hours, and max (A) maximum historical traffic data of the base station to be monitored in historical busy hours;
obtaining a second traffic weight according to the predicted traffic data of the base station to be monitored in idle time within the preset time period and the historical traffic data of the base station to be monitored in historical idle time, and specifically comprising:
calculating and obtaining the second flow weight according to a second formula, wherein the second formula specifically comprises:
wherein, ω is 2 Is the second traffic weight, B pre The traffic data of the base station to be monitored in idle in a preset time period is represented, min (B) is minimum historical traffic data of the base station to be monitored in historical idle, and max (B) is maximum historical traffic data of the base station to be monitored in historical idle.
7. The method for monitoring base station abnormality according to claim 5, wherein the processing the first traffic weight and the second traffic weight to obtain the traffic weight of the base station to be monitored specifically includes:
calculating and obtaining the flow weight of the base station to be monitored according to a third formula, wherein the third formula specifically comprises:
ω=αω 1 +βω 2
and omega is the traffic weight of the base station to be monitored, alpha is the proportion coefficient of the first traffic weight, and beta is the proportion coefficient of the second traffic weight.
8. An apparatus for monitoring base station abnormality, comprising:
the acquisition module is used for acquiring the predicted flow data of the base station to be monitored in busy and idle states within a preset time period and historical flow data of the base station to be monitored in historical busy and idle states;
the processing module is used for determining the flow weight of the base station to be monitored according to the predicted flow data of the base station to be monitored in busy and idle time within a preset time period and the historical flow data of the base station to be monitored in historical busy and idle time;
and responding to the processing module, and if the traffic weight is larger than a preset weight threshold, determining that the base station to be monitored has invisible abnormality.
9. A monitoring device, comprising: a memory and a processor;
the memory stores computer execution instructions;
the processor executes computer-executable instructions stored by the memory to implement the method of any of claims 1 to 7.
10. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211001605.3A CN115334560B (en) | 2022-08-19 | 2022-08-19 | Base station abnormality monitoring method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211001605.3A CN115334560B (en) | 2022-08-19 | 2022-08-19 | Base station abnormality monitoring method, device, equipment and computer readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115334560A true CN115334560A (en) | 2022-11-11 |
CN115334560B CN115334560B (en) | 2024-05-07 |
Family
ID=83925824
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211001605.3A Active CN115334560B (en) | 2022-08-19 | 2022-08-19 | Base station abnormality monitoring method, device, equipment and computer readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115334560B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116321243A (en) * | 2023-01-05 | 2023-06-23 | 杭州纵横通信股份有限公司 | Mobility management method of base station |
CN117793746A (en) * | 2023-12-01 | 2024-03-29 | 江苏全创电子科技有限公司 | Base station equipment management method and system based on big data |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009071428A (en) * | 2007-09-11 | 2009-04-02 | Hitachi Communication Technologies Ltd | Device and method for monitoring fault in radio base station |
US20150350935A1 (en) * | 2014-05-29 | 2015-12-03 | Fujitsu Limited | Monitoring device and monitoring system |
CN110888788A (en) * | 2019-10-16 | 2020-03-17 | 平安科技(深圳)有限公司 | Anomaly detection method and device, computer equipment and storage medium |
CN111130940A (en) * | 2019-12-26 | 2020-05-08 | 众安信息技术服务有限公司 | Abnormal data detection method and device and server |
CN111163484A (en) * | 2018-11-07 | 2020-05-15 | 中国移动通信集团湖南有限公司 | Base station fault prediction method and device |
CN111178598A (en) * | 2019-12-16 | 2020-05-19 | 中国铁道科学研究院集团有限公司 | Passenger flow prediction method and system for railway passenger station, electronic device and storage medium |
CN111881961A (en) * | 2020-07-17 | 2020-11-03 | 国网江苏省电力有限公司苏州供电分公司 | Power distribution network fault risk grade prediction method based on data mining |
CN112492630A (en) * | 2019-09-11 | 2021-03-12 | 中国电信股份有限公司 | Fault prediction method and device of base station equipment and base station |
CN113068212A (en) * | 2020-01-02 | 2021-07-02 | 广东博智林机器人有限公司 | Abnormal base station detection method and device, storage medium and electronic equipment |
CN114172708A (en) * | 2021-11-30 | 2022-03-11 | 北京天一恩华科技股份有限公司 | Method for identifying network flow abnormity |
-
2022
- 2022-08-19 CN CN202211001605.3A patent/CN115334560B/en active Active
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009071428A (en) * | 2007-09-11 | 2009-04-02 | Hitachi Communication Technologies Ltd | Device and method for monitoring fault in radio base station |
US20150350935A1 (en) * | 2014-05-29 | 2015-12-03 | Fujitsu Limited | Monitoring device and monitoring system |
CN111163484A (en) * | 2018-11-07 | 2020-05-15 | 中国移动通信集团湖南有限公司 | Base station fault prediction method and device |
CN112492630A (en) * | 2019-09-11 | 2021-03-12 | 中国电信股份有限公司 | Fault prediction method and device of base station equipment and base station |
CN110888788A (en) * | 2019-10-16 | 2020-03-17 | 平安科技(深圳)有限公司 | Anomaly detection method and device, computer equipment and storage medium |
CN111178598A (en) * | 2019-12-16 | 2020-05-19 | 中国铁道科学研究院集团有限公司 | Passenger flow prediction method and system for railway passenger station, electronic device and storage medium |
CN111130940A (en) * | 2019-12-26 | 2020-05-08 | 众安信息技术服务有限公司 | Abnormal data detection method and device and server |
CN113068212A (en) * | 2020-01-02 | 2021-07-02 | 广东博智林机器人有限公司 | Abnormal base station detection method and device, storage medium and electronic equipment |
CN111881961A (en) * | 2020-07-17 | 2020-11-03 | 国网江苏省电力有限公司苏州供电分公司 | Power distribution network fault risk grade prediction method based on data mining |
CN114172708A (en) * | 2021-11-30 | 2022-03-11 | 北京天一恩华科技股份有限公司 | Method for identifying network flow abnormity |
Non-Patent Citations (1)
Title |
---|
刘燮鹏: "基于机器学习的移动基站设备故障预警系统研究", 《中国优秀硕士学位论文辑》, 15 July 2020 (2020-07-15) * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116321243A (en) * | 2023-01-05 | 2023-06-23 | 杭州纵横通信股份有限公司 | Mobility management method of base station |
CN116321243B (en) * | 2023-01-05 | 2023-09-26 | 杭州纵横通信股份有限公司 | Mobility management method of base station |
CN117793746A (en) * | 2023-12-01 | 2024-03-29 | 江苏全创电子科技有限公司 | Base station equipment management method and system based on big data |
Also Published As
Publication number | Publication date |
---|---|
CN115334560B (en) | 2024-05-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102882745B (en) | A kind of method and apparatus for monitoring business server | |
CN115334560B (en) | Base station abnormality monitoring method, device, equipment and computer readable storage medium | |
AU2019201687B2 (en) | Network device vulnerability prediction | |
CN113473514B (en) | Electric power wireless private network fault diagnosis model training method, diagnosis method and apparatus | |
EP2997756B1 (en) | Method and network device for cell anomaly detection | |
CN111579923B (en) | Power distribution network fault diagnosis system and method | |
US10548036B2 (en) | Fault monitoring by assessing spatial distribution of queries in a utility supply network | |
CN110891283A (en) | Small base station monitoring device and method based on edge calculation model | |
CN109150565B (en) | Network situation perception method, device and system | |
CN109873499A (en) | Intelligent distribution area management terminal | |
CN112134357A (en) | Power distribution automation master station system based on cloud service | |
CN113570277A (en) | Power capacity management method and device | |
CN117938277A (en) | Indoor antenna monitoring system | |
CN115865611A (en) | Fault processing method and device of network equipment and electronic equipment | |
CN113780595A (en) | Method for first-aid repair of base station in case of power failure and data analysis server | |
CN113923096B (en) | Network element fault early warning method and device, electronic equipment and storage medium | |
CN115511296A (en) | Park energy efficiency integrated management method, system, equipment and storage medium | |
CN114036711A (en) | Network quality degradation detection method and system | |
CN118200949B (en) | Fault monitoring system and method for communication equipment | |
CN112291804B (en) | Service fault diagnosis method for noise network under 5G network slice | |
US20240070622A1 (en) | Methods and internet of things (iot) systems for full-cycle management of smart gas equipment based on big data | |
US20240340217A1 (en) | System and method for optimizing fault detection in internet of things network | |
CN117834540B (en) | Communication optimization method based on ultrasonic water meter, internet of things system and equipment | |
CN113973329B (en) | Method, device, equipment and storage medium for early warning of mobile base station service withdrawal | |
CN116937794B (en) | Electric power control detection system and method |
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 |