CN114630352B - Fault monitoring method and device for access equipment - Google Patents
Fault monitoring method and device for access equipment Download PDFInfo
- Publication number
- CN114630352B CN114630352B CN202011463665.8A CN202011463665A CN114630352B CN 114630352 B CN114630352 B CN 114630352B CN 202011463665 A CN202011463665 A CN 202011463665A CN 114630352 B CN114630352 B CN 114630352B
- Authority
- CN
- China
- Prior art keywords
- operating parameters
- access device
- parameter
- target
- target access
- 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.)
- Active
Links
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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
本发明公开了一种接入设备的故障监测方法和装置，用以解决确定接入设备的故障类型不准确的问题。本方案包括：获取样本接入设备的参数样本集和目标接入设备在多种运行状态下的历史运行参数；根据参数样本集确定目标接入设备在每种运行状态下的历史运行参数分别匹配的目标数据类型标签；确定与目标数据类型标签相匹配的监测模型；根据监测模型监测目标接入设备，以在目标接入设备的运行参数与异常运行参数相匹配时根据异常运行参数相匹配的故障类型确定目标接入设备的故障类型。本方案无需人工巡检，能高效实现故障监测。由于监测模型是与目标接入设备相匹配的，能提高确定的故障类型的准确度。
The invention discloses a fault monitoring method and device for access equipment, which are used to solve the problem of inaccurate determination of the fault type of the access equipment. This solution includes: obtaining the parameter sample set of the sample access device and the historical operating parameters of the target access device in various operating states; determining the matching of the historical operating parameters of the target access device in each operating state according to the parameter sample set The target data type label; determine the monitoring model that matches the target data type label; monitor the target access device according to the monitoring model, so that when the operating parameters of the target access device match the abnormal operating parameters, match the abnormal operating parameters The fault type determines the fault type of the target access device. This solution does not require manual inspection, and can efficiently realize fault monitoring. Since the monitoring model is matched with the target access device, the accuracy of the determined fault type can be improved.
Description
Technical Field
The present invention relates to the field of fault monitoring, and in particular, to a fault monitoring method and apparatus for an access device.
Background
In an industrial internet application scenario in the 5G technical field, fig. 1 shows a communication system including a plurality of access devices, where a plurality of access devices of a user may be converged by a switch and then connected to a CPE (Customer Premise Equipment) terminal through an access AR router. And then, the signals can be split through communication equipment such as 5G base stations (gNodeB), transmission equipment slice packet networks (Slicing Packet Network, SPN) and UPF (user plane function) equipment, so as to realize the transmission of the signals of the access equipment. And then the data is transmitted to the central control equipment through the convergence AR and the exchanger to realize data collection and monitoring.
Although the operation states of the CPE terminal and the upstream equipment can be monitored in the prior art, monitoring of each access equipment which is connected with the access AR router in a communication way and is arranged at the downstream of the CPE terminal is difficult to realize, and the access equipment cannot be known in time when the access equipment fails. If the engineer monitors the running state of each access device in a patrol way, more manpower is required, and the monitoring instantaneity is poor. Moreover, the monitoring effect is influenced by subjective consciousness of engineers, and the type of faults is difficult to accurately judge.
How to efficiently determine the fault type of the access equipment is the technical problem to be solved by the application.
Disclosure of Invention
The embodiment of the application aims to provide a fault monitoring method and device for access equipment, which are used for solving the problem of inaccurate fault type determination of the access equipment.
In a first aspect, a method for monitoring a fault of an access device is provided, including:
acquiring a parameter sample set of sample access equipment and historical operation parameters of target access equipment in various operation states, wherein the parameter training sample set comprises sample operation parameters of the sample access equipment marked with data type labels;
determining target data type labels respectively matched with historical operation parameters of the target access equipment in each operation state according to the parameter sample set;
determining a monitoring model matched with the target data type tag, wherein the monitoring model comprises an abnormal operation parameter and a fault type matched with the abnormal operation parameter;
and monitoring the target access equipment according to the monitoring model, and determining the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter.
In a second aspect, there is provided a fault monitoring apparatus for an access device, including:
The system comprises an acquisition module, a parameter training sample set and a data type label acquisition module, wherein the acquisition module acquires a parameter sample set of sample access equipment and historical operation parameters of target access equipment in various operation states, and the parameter training sample set comprises sample operation parameters of the sample access equipment, which are marked with the data type label;
the first determining module is used for determining target data type labels respectively matched with historical operation parameters of the target access equipment in each operation state according to the parameter sample set;
the second determining module is used for determining a monitoring model matched with the target data type label, wherein the monitoring model comprises an abnormal operation parameter and a fault type matched with the abnormal operation parameter;
and the monitoring module monitors the target access equipment according to the monitoring model so as to determine the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter.
In a third aspect, there is provided an electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, the computer program implementing the steps of the method as in the first aspect when executed by the processor.
In a fourth aspect, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method as in the first aspect.
In the embodiment of the application, a parameter sample set of the sample access equipment and historical operation parameters of the target access equipment in various operation states are obtained; determining target data type labels respectively matched with historical operation parameters of the target access equipment in each operation state according to the parameter sample set; determining a monitoring model matched with the target data type tag; and monitoring the target access equipment according to the monitoring model so as to determine the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter. The scheme does not need manual inspection, and can efficiently realize fault monitoring. Since the monitoring model is matched with the target access device, the accuracy of the determined fault type can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
Fig. 1 is a schematic diagram of a communication system including a plurality of access devices;
FIG. 2 is a flow chart of a method for monitoring access device for failure according to the present application;
FIG. 3a is a second flow chart of a fault monitoring method of an access device according to the present application;
FIG. 3b is a schematic representation of stationary sample operating parameters of the present application;
FIG. 3c is a schematic representation of the fluctuating sample operating parameters of the present application;
FIG. 3d is a schematic representation of periodic sample operating parameters of the present application;
FIG. 3e is a schematic diagram of the recovery of sample operating parameters of the present application;
FIG. 4 is a third flow chart of a fault monitoring method of an access device according to the present application;
FIG. 5 is a flow chart of a fault monitoring method for an access device according to the present application;
FIG. 6 is a flow chart of a method for monitoring access device for failure according to the present application;
FIG. 7a is a schematic structural diagram of a fault monitoring device for an access device according to the present application;
FIG. 7b is a second schematic diagram of a fault monitoring device for an access device according to the present application;
fig. 7c is a third schematic structural diagram of a fault monitoring device for an access device according to the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. The reference numerals in the present application are only used for distinguishing the steps in the scheme, and are not used for limiting the execution sequence of the steps, and the specific execution sequence controls the description in the specification.
The scheme provided by the embodiment of the application can be applied to the fields of enterprise park management, residential community management and the like, and can be used for timely monitoring the faults of the access equipment and determining the fault types. In this embodiment, enterprise campus management is taken as an example.
Access devices within an enterprise campus include, for example, high definition cameras, network phones, industrial robots, sensors, programmable logic controller (Programmable Logic Controller, PLC) devices, etc. The information sent by the access devices can be converged through the switch, then connected to the CPE terminal through the access AR router, and then shunted through the UPF device through the 5G base station and the transmission device. Such as to a central server in the campus or to a large network of operators, etc.
The access AR router is a single node, once the failure possibly causes that the business in the enterprise park cannot be normally used, and the service quality of the 5G industry clients is difficult to guarantee. The embodiment of the application provides a fault monitoring method of access equipment for solving the problems in the prior art, which can be applied to 5G industry units, and is particularly suitable for industries with higher Service-Level Agreement (SLA).
An embodiment of the present application provides a fault monitoring method for an access device, where an execution body of the embodiment may be an access AR router, as shown in fig. 2, including:
s21: and acquiring a parameter sample set of the sample access equipment and historical operation parameters of the target access equipment in various operation states, wherein the parameter training sample set comprises sample operation parameters of the sample access equipment marked with data type labels.
In this embodiment, the access device may include, for example, a high-definition camera, a sensor, and other devices. When an access device disconnects from a switch or an access AR router connected upstream thereof due to network connectivity or other reasons, the number of access devices accessing the AR router becomes small, and the port state of the disconnected access device tends to be changed from up to down.
When the port rate and the duplex mode are set to auto-negotiation, if the transmission quality of the connection line of a certain access device is poor, the port negotiation rate corresponding to the access device may be automatically reduced, for example, 1000Mbps is reduced to 100Mbps, the duplex mode is changed from full duplex to half duplex, the input flow and the output flow corresponding to the port are suddenly reduced, and the situations of packet loss, time delay increase and the like exist in the ping test.
In this step, the instruction may be used to periodically collect and parse the performance parameter and the state information of the sample access device on the access AR router to obtain the sample operation parameter, so as to generate a parameter sample set of the sample access device. The acquisition period can be set to be several seconds, several minutes, several hours or several days according to actual requirements, such as 30 seconds, 1 minute, 15 minutes or 1 hour, etc., which is not limited by the present application.
The sample operation parameters include, but are not limited to, the number of access devices MAC (Media Access Control), details of MAC addresses and IP addresses of each access device, port status of the access devices, port duplex mode, throughput, central processing unit (Central Processing Unit, CPU) utilization, memory utilization, input rate and output rate of each port in a certain period of time, port negotiation rate, delay, packet loss, jitter, and the like. In addition to the various parameters listed above, the sample operating parameters may also include other types of parameters that characterize the operating state of the access device.
The number of sample operation parameters in the parameter sample set is often multiple, and the sample operation parameters can be collected historical data, and data type labels respectively corresponding to the sample operation parameters are manually marked or automatically generated in a data processing mode. The sample operating parameters in the parameter sample set may be from one access device or may be from a plurality of different access devices.
In the embodiment of the application, the target access device can be the access device needing to be monitored. In order to realize effective fault monitoring on the target access equipment in various states, historical operation parameters of the target access equipment in various operation states are obtained in the embodiment. The operation state may be a state preset manually, or may refer to a state of the access device under different scenes or conditions. For example, the operating state may include a state in which the target access device is daily functioning normally, a maintenance state when a cutover, upgrade, or overhaul is performed, and the like. The trend of fluctuation of the operating parameters of the target access device tends to be different in each state. The embodiment of the application acquires the historical operation parameters in various states, and can be favorable for determining the monitoring model matched with the target access equipment in the subsequent steps so as to realize effective monitoring on the target access equipment in each state.
Optionally, in order to improve the accuracy of fault monitoring, further diagnose the fault and determine a solution to the fault, the application may also preprocess the operation parameters of each sample before generating the parameter sample set. The preprocessing may include, for example, null interpolation, such as interpolation by median, mean, mode, or the like. The method can further comprise preprocessing steps such as data normalization and the like, so that the quality of the acquired sample operation parameters is improved, and the data quality of the parameter sample set is improved.
S22: and determining target data type labels with respectively matched historical operation parameters of the target access equipment in each operation state according to the parameter sample set.
In this step, the historical operating parameters of the target access device in each operating state may be compared based on the sample operating parameters marked with the data type tag. According to the fluctuation trend of the parameters, the numerical range and other parameter characteristics, determining sample operation parameters corresponding to the historical operation parameters in each operation state, and further determining the data type label marked by the corresponding sample operation parameters as the target data type label of the historical operation parameters in each operation state. The target data type tag can characterize the fluctuation characteristics of the operating parameters of the target access device in one operating state.
S23: and determining a monitoring model matched with the target data type label, wherein the monitoring model comprises an abnormal operation parameter and a fault type matched with the abnormal operation parameter.
The monitoring model in this embodiment is one or more models matched with the target data type tag, and the abnormal operation parameter may refer to an operation parameter when an abnormality occurs in the access device. The monitoring model is matched with the target data type label, and the target data type label can reflect fluctuation characteristics of the operating parameters of the target access equipment in all operating states, so that the determined monitoring model can effectively monitor the operating parameters of the target access equipment in all operating states.
Based on the solution provided in the foregoing embodiment, optionally, a monitoring model matched with the target data type tag may be determined in this step based on a decision tree algorithm. In practical applications, the monitoring model may be determined according to other algorithms. Specifically, the operation parameters of the target access device can be classified according to a parameter sample set which is obtained in advance and consists of various types of sample operation parameters, and an abnormal monitoring model with highest matching degree is determined based on a decision tree algorithm, so that the automatic monitoring of the state of the access device is realized, and the real-time early warning of the monitored abnormal problem can be realized.
S24: and monitoring the target access equipment according to the monitoring model, and determining the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter.
Because the monitoring model comprises the abnormal operation parameters and the matched fault types, the target access equipment can be monitored timely and accurately according to the determined monitoring model in the step, so that the matched fault types are determined, and the real-time monitoring and accurate diagnosis of the access equipment faults are realized.
According to the scheme provided by the embodiment of the application, a parameter sample set of the sample access equipment and historical operation parameters of the target access equipment in various operation states are obtained; determining target data type labels respectively matched with historical operation parameters of the target access equipment in each operation state according to the parameter sample set; determining a monitoring model matched with the target data type tag; and monitoring the target access equipment according to the monitoring model so as to determine the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter. The scheme does not need manual inspection, and can efficiently realize fault monitoring. Since the monitoring model is matched with the target access device, the accuracy of the determined fault type can be improved.
Based on the solution provided in the foregoing embodiment, optionally, step S22 includes determining, according to the parameter sample set, a target data type tag that is respectively matched with the historical operation parameters of the target access device in each operation state, as shown in fig. 3a, where the method includes:
s31: and determining the parameter curve characteristics of the target historical operating parameters of the target access equipment in the target operating state.
The target historical operating parameters may be discrete parameter points or continuous parameter curves. If the target historical operating parameter is a discrete parameter point, a parameter curve may be generated from a plurality of parameter points based on time. In this step, the parameter curve characteristics are determined from the parameter curve of the target access device. The characteristics of the parameter curve can comprise the characteristics of fluctuation trend, numerical value, fluctuation frequency, fluctuation amplitude and the like of the parameter curve.
S32: and determining target sample operation parameters matched with the parameter curve characteristics in the parameter sample set.
And determining matched target sample operation parameters from the parameter sample set according to the parameter curve characteristics determined in the steps. In other words, the target sample operating parameters in the parameter sample set that are characterized by the parameter curve described above are determined. And if the determined target sample operation parameters have the same curve characteristics as the target historical operation parameters, determining that the operation parameter change characteristics of the target access equipment in the target operation state are consistent with the target sample operation parameters.
S33: and determining the data type label marked by the target sample operation parameter as the target data type label of the target historical operation parameter.
The data type label of the target sample operation parameter mark can represent the change characteristic of the target sample operation parameter, and the parameter change characteristic of the target sample operation parameter is matched with the parameter curve characteristic of the target historical operation parameter, so that the target historical operation parameter also has the parameter change characteristic represented by the target data type label.
According to the scheme provided by the embodiment of the application, the target data type label of the target historical operating parameter can be determined according to the curve characteristic of the operating parameter, and the determined target data type label can accurately reflect the parameter change trend of the target access equipment in the target operating state, so that the monitoring model matched with the target access equipment is determined in the subsequent step, and the fault monitoring accuracy is improved.
Based on the solution provided in the foregoing embodiment, optionally, the parameter training sample set includes at least one of the following sample operation parameters of the sample access device:
stationary sample operation parameters marked with stationary labels, as shown in fig. 3b, the parameter values of which are unchanged;
the wave sample operation parameters marked with the wave type labels, as shown in fig. 3c, include at least one wave peak with a wave peak value larger than a preset operation parameter range;
A periodic sample operation parameter marked with a periodic tag, as shown in fig. 3d, whose parameter value periodically fluctuates;
the recovery sample operation parameters marked with the recovery type label include, as shown in fig. 3e, a trough with a trough value smaller than a preset operation parameter, and at least a part of parameter values after the trough are larger than any parameter value before the trough.
According to the invention, the sample operation parameters are divided into stable type, fluctuation type, periodic type and recovery type according to the data index characteristics in each scene. The stationary type may represent an operation parameter in which the data index is unchanged or remains stationary, such as a port state, a port duplex mode, a port negotiation rate, etc. in a daily scenario. The fluctuation type may refer to an operation parameter that is unstable, has no obvious periodic characteristics, and contains large fluctuation, such as input and output flow of each port in daily and changing scenes. Periodic may refer to operating parameters that have periodic patterns that occur periodically, such as during busy hours in a daily scenario, throughput, etc. The recovery type may refer to changing operation parameters, such as the number of access devices in upgrading, cutting or overhauling operations, which slowly climb or gradually rise after the traffic falls in the pit in the adjustment process.
In addition to the four types listed above in the embodiments of the present application, the parameter training sample set may also include other types of sample operating parameters according to actual needs. According to the scheme parameter training sample set provided by the embodiment of the application, the sample operation parameters with obvious characteristics of the access equipment are contained, the data type label of the historical operation parameters of the target access equipment can be accurately determined according to various sample operation parameters with the obvious characteristics, and the matching property of the data type label and the historical operation parameters of the access equipment is improved.
Optionally, based on the four types listed above, the monitoring model determined in step S23 includes at least the following four types:
(1) Stable type
When the target data type tag includes a stationary type, the abnormal operating parameter of the monitoring model may refer to an operating parameter that fluctuates. For example, if the port state corresponding to an access device in a daily scenario changes from up to down, it indicates that the operation parameter fluctuates, and the fault type may be a connection interruption.
For another example, if the negotiation rate of a port automatically decreases or the duplex mode is changed from full duplex to half duplex, it may be determined that the transmission quality of the port decreases, which may cause the connection of the access device of the port to be interrupted.
(2) Of the wave type
When the target data type tag comprises a fluctuation type, a static threshold value, a dynamic fluctuation amplitude exceeding threshold value or a double monitoring mode combining the two threshold values can be set. The abnormal operation parameters of the fluctuation type monitoring model may include, for example, an operation parameter with a peak value exceeding a preset static threshold value and an operation parameter with a fluctuation amplitude exceeding a preset fluctuation amplitude, and the fault type may be preset according to the fluctuation amplitude and the fluctuation peak value according to the type of the access device.
For example, if the bandwidth utilization ratio of the input flow of a certain port is set to be higher than 60%, 70% or 80%, the third-level alarm, the second-level alarm and the first-level alarm are triggered respectively, or if the input flow obtained at a certain acquisition time exceeds the fluctuation range of the input flow ring ratio obtained at the previous acquisition time by more than 20%, 30% or 40%, the third-level alarm, the second-level alarm and the first-level alarm are triggered respectively.
(3) Periodic type
When the target data type tag includes a periodic pattern, it indicates that the operating parameter has a periodic pattern that occurs periodically, and for the periodic index, a corresponding period of variation may be determined from the historical operating parameter. Based on the determined change period, the abnormal operation parameters may include operation parameters in which the change period of the operation parameters does not match the determined change period, or the corresponding fault type may be preset according to the period length change of the abnormal operation parameters in combination with the type of the access device.
(4) Recovery type
The recovery type operation parameter may refer to an operation parameter that is gradually increased after a pit is dropped by an upgrade, cutover or repair operation (e.g., the number of access devices). After the adjustment, the operation parameters tend to change under the influence of the adjustment, and whether the operation parameters are abnormal or not can be judged according to the operation parameter values before and after pit falling fluctuation.
For example, when the purpose of the above-described adjustment operation is to reduce the load for the high-load apparatus, the adjusted load operation parameter should be lower than the load operation parameter before the fluctuation, that is, the abnormal operation parameter may refer to an operation parameter whose value after the fluctuation is not smaller than the parameter value before the fluctuation.
For another example, when the purpose of the above adjustment operation is to improve the data throughput, the adjusted throughput operation parameter should be higher than the throughput operation parameter before the fluctuation, that is, the abnormal operation parameter may refer to an operation parameter in which the parameter after the fluctuation is not greater than the parameter value before the fluctuation.
The corresponding fault type can be preset according to the actual purpose of the adjustment operation, the type of the access equipment and the operation parameters before adjustment.
Based on the solution provided in the foregoing embodiment, optionally, after determining, according to the parameter sample set, a target data type tag that is respectively matched with a historical operation parameter of the target access device in each operation state, as shown in fig. 4, the method further includes:
S41: and updating the parameter sample set according to the historical operation parameters of the target access equipment in each operation state and the respectively matched target data type labels.
In this step, the existing parameter sample set may be updated based on the target data type tag and the historical operating parameters in the matched operating state. If the target data type label in multiple operation states of the target access device has other characteristics, a new data type label can be generated according to the target data type label in multiple operation states, and the label types in the parameter sample set are increased. Or, the existing type tag can be split into multiple sub-tags according to the target data type tag in multiple running states, for example, the fluctuation type tag is split into a fluctuation ascending type tag, a fluctuation descending type tag and a stable fluctuation type tag, and the existing data type tag is further divided according to the fluctuation trend of running parameter fluctuation.
By the scheme provided by the embodiment of the application, the parameter sample set can be updated, so that the data type label and the matched sample operation parameters in the parameter sample set are applicable to various practical application scenes.
Based on the solution provided in the foregoing embodiment, optionally, after monitoring the target access device according to the monitoring model in step S24, as shown in fig. 5, the method further includes:
s51: and determining the abnormal operation parameters in the operation parameters of the target access equipment when the operation parameters of the target access equipment are matched with the abnormal operation parameters.
The number of the determined abnormal operation parameters can be one or more, and in practical application, the number of the abnormal operation parameters is a plurality of the abnormal operation parameters possibly due to a certain correlation among the abnormal operation parameters. Such as increased throughput, the CPU load tends to increase.
S52: and when the number of the abnormal operation parameters is single, determining the fault type of the target access equipment according to the association relation between the abnormal operation parameters and other operation parameters, wherein the other operation parameters comprise the operation parameters of the target access equipment except the abnormal operation parameters.
If the abnormal operating parameter is singular, it may be determined that the fault is associated with the abnormal operating parameter on the one hand and that the fault does not affect other operating parameters associated with the abnormal operating parameter on the other hand. The fault type of the target access equipment can be accurately determined based on the association relation among the operation parameters and the variation of the abnormal operation parameters.
Aiming at a single-index abnormal scene, the automatic fault bounding analysis can be carried out in two cases: besides the abnormal early warning of a certain index, a) if other key performance indexes with obvious fluctuation (but the fluctuation amplitude does not reach the abnormal early warning threshold) exist at the same time, the correlation between the abnormal index and other fluctuation indexes can be analyzed by using a CoFlux algorithm, namely, the fluctuation correlation, the sequence of fluctuation and the fluctuation direction among different time sequences are judged based on the historical data analysis of a plurality of time sequences, and further, the fault delimitation is assisted based on the multi-index correlation analysis. b) If other obviously fluctuating key performance indexes do not exist at the same time, fault delimitation is realized by adopting a preset rule and other methods. For example, the preset rules are:
if the port state corresponding to an access device is found to be changed from up to down on the AR router, the fault type is that the access device is disconnected from the AR router, and the diagnosis proposal is to check whether the transmission line and the data configuration are normal.
S53: and when the number of the abnormal operation parameters is a plurality of, determining the fault type of the target access equipment according to the association relation among the abnormal operation parameters.
When the number of abnormal operating parameters is plural, it is generally caused by a fault affecting a plurality of interrelated operating parameters. And determining the type of the actually-occurring fault according to the association relation among the abnormal operation parameters.
Based on the solution provided in the foregoing embodiment, optionally, when the number of the abnormal operation parameters is plural, step S53 is described above, where determining the fault type of the target access device according to the association relationship between the plural abnormal operation parameters, as shown in fig. 6, includes:
s61: and determining pearson correlation coefficients of a plurality of abnormal operation parameters, wherein the pearson correlation coefficients represent the association relation among the abnormal operation parameters.
S62: and determining a weight value between the fault of the target access equipment and each abnormal operation parameter according to the Pearson correlation coefficient.
S63: and determining the fault type of the target access equipment according to the weight value between the fault of the target access equipment and each abnormal operation parameter.
When the number of the abnormal operation parameters is multiple, it is often meant that some potential faults occur in the access device, such as disconnection between the access device and the router or degradation of transmission quality caused by transmission line problems or abnormal data configuration. According to the scheme, the fault duration is greatly shortened by carrying out automatic delimitation analysis on the abnormal early warning problem, and the service quality of a 5G industry unit is effectively improved.
Aiming at a multi-index abnormal scene, the invention uses the Pearson algorithm to analyze the association relation between the historical fault information and a plurality of abnormal operation parameters, and constructs a multi-index association model based on the association relation, thereby carrying out automatic fault analysis on the access equipment based on the multi-index association model, improving the analysis efficiency of the association of indexes or state anomalies and the fault of the access equipment, being beneficial to quickly determining the fault reason of the access equipment and greatly shortening the fault duration.
The Pearson correlation coefficient represents the degree of tightness of two correlation factors, and the larger the absolute value is, the stronger the correlation is, and the smaller the absolute value is, the weaker the correlation is. The Pearson correlation coefficient between the two variables X and Y is defined as the quotient of the covariance and standard deviation between the two variables X and Y, as shown in equation (1):
and estimating the Pearson correlation coefficient of the two variable samples, expressed by the formula (2), whereinAnd->Respectively sample X i And Y i Average value of (2).
The association relation information in the invention refers to carrying out Pearson correlation analysis on each abnormal operation parameter of the access equipment based on the formula (2) according to the fault time, determining the association weight relation between the actually-generated fault and a plurality of abnormal operation parameters, and determining a multi-index association model according to the association weight relation.
For example, pearson correlation analysis is performed on the historical failure and the plurality of abnormal operation parameters on the AR router, and it is determined that the access device failure is related to the number of MACs, the MAC and IP information of the corresponding terminal, the state of the corresponding port, the traffic index of the corresponding port, and the like. And the association degree of the abnormal number of the MAC and the fault of the access equipment is 0.32, the association degree of the abnormal number of the MAC and the fault (such as missing) of the IP information of the corresponding terminal and the fault of the access equipment is 0.75, the association degree of the abnormal state of the corresponding port and the fault of the access equipment is 0.7, and the association degree of the abnormal flow of the corresponding port and the fault of the access equipment is 0.45, so that the fault type can be determined according to the association degree.
According to the scheme provided by the embodiment of the application, on the premise that the downstream access equipment of the CPE terminal of the 5G industry unit has no professional network management, the fault monitoring and diagnosis of the access equipment can be automatically realized, the fault type is accurately determined, and the fault removal and maintenance are facilitated. According to the scheme provided by the embodiment of the application, firstly, the sample operation parameters which can represent key performance or state such as an MAC address, a port state, throughput and the like are acquired on the access AR router by utilizing the periodical acquisition of instructions, and the data type labels are respectively marked. And then, determining the obtained target data type label matched with the historical operation parameters of the target access equipment in each operation state. The monitoring model corresponding to the tag is determined by one or more of a stationary type, a fluctuation type, a periodic type and a recovery type. And then, classifying according to a training sample set formed by various types of training samples and the characteristics of key performance or state data acquired in real time, and automatically matching the optimal abnormal monitoring model for different types of data based on a decision tree algorithm to realize automatic monitoring of the state of the access equipment and real-time early warning of abnormal problems. The scheme provided by the embodiment also provides a corresponding automatic fault delimiting method for distinguishing two scenes of single-index abnormality and multi-index abnormality, so that the operation and maintenance efficiency is greatly improved, the fault duration is effectively shortened, the service quality of 5G industry clients is ensured, and a powerful network support is provided for 5G 2B service development.
In order to solve the problems in the prior art, an embodiment of the present application further provides a fault monitoring device 70 of an access device, as shown in fig. 7a, including:
an obtaining module 71, configured to obtain a parameter sample set of a sample access device and historical operation parameters of a target access device in multiple operation states, where the parameter training sample set includes sample operation parameters of the sample access device marked with a data type tag;
a first determining module 72, configured to determine, according to the parameter sample set, a target data type tag that is respectively matched with a historical operation parameter of the target access device in each operation state;
a second determining module 73 that determines a monitoring model that matches the target data type tag, the monitoring model including an abnormal operation parameter and a fault type that matches the abnormal operation parameter;
the monitoring module 74 monitors the target access device according to the monitoring model to determine a fault type of the target access device according to a fault type of the abnormal operation parameter when the operation parameter of the target access device matches the abnormal operation parameter.
Optionally, the first determining module 72 is configured to:
Determining a parameter curve characteristic of a target historical operation parameter of the target access equipment in a target operation state;
determining target sample operation parameters matched with the parameter curve characteristics in the parameter sample set;
and determining the data type label marked by the target sample operation parameter as the target data type label of the target historical operation parameter.
Optionally, the parameter training sample set includes at least one of the following sample operating parameters of the sample access device:
a stationary sample operating parameter marked with a stationary label, the stationary sample operating parameter having a constant parameter value;
the wave sample operation parameters marked with the wave type labels comprise at least one wave peak of which the wave peak value is larger than a preset operation parameter range;
a periodic sample operation parameter marked with a periodic tag, the parameter value of the periodic sample operation parameter periodically fluctuates and changes;
a recovery sample operating parameter marked with a recovery tag, the recovery sample operating parameter comprising a trough having a trough value less than a preset operating parameter, and at least a portion of the parameter values after the trough being greater than any of the parameter values before the trough.
Optionally, as shown in fig. 7b, the apparatus further comprises an update module 75 for:
and updating the parameter sample set according to the historical operation parameters of the target access equipment in each operation state and the respectively matched target data type labels.
Optionally, as shown in fig. 7c, a third determining module 76 is further included for:
determining an abnormal operation parameter in the operation parameters of the target access equipment when the operation parameters of the target access equipment are matched with the abnormal operation parameters;
when the number of the abnormal operation parameters is single, determining the fault type of the target access equipment according to the association relation between the abnormal operation parameters and other operation parameters, wherein the other operation parameters comprise the operation parameters of the target access equipment except the abnormal operation parameters;
and when the number of the abnormal operation parameters is a plurality of, determining the fault type of the target access equipment according to the association relation among the abnormal operation parameters.
Optionally, the third determining module 76 is configured to:
determining pearson correlation coefficients of a plurality of abnormal operation parameters, wherein the pearson correlation coefficients represent the association relation among the abnormal operation parameters;
Determining a weight value between the fault of the target access equipment and each abnormal operation parameter according to the Pearson correlation coefficient;
and determining the fault type of the target access equipment according to the weight value between the fault of the target access equipment and each abnormal operation parameter.
Optionally, the second determining module 73 is configured to:
and determining a monitoring model matched with the target data type label based on a decision tree algorithm.
By the device provided by the embodiment of the application, a parameter sample set of the sample access equipment and historical operation parameters of the target access equipment in various operation states are obtained; determining target data type labels respectively matched with historical operation parameters of the target access equipment in each operation state according to the parameter sample set; determining a monitoring model matched with the target data type tag; and monitoring the target access equipment according to the monitoring model so as to determine the fault type of the target access equipment according to the fault type matched with the abnormal operation parameter when the operation parameter of the target access equipment is matched with the abnormal operation parameter. The scheme does not need manual inspection, and can efficiently realize fault monitoring. Since the monitoring model is matched with the target access device, the accuracy of the determined fault type can be improved.
Preferably, the embodiment of the present invention further provides an electronic device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor, where the computer program when executed by the processor implements each process of the foregoing embodiment of the fault monitoring method of an access device, and the process can achieve the same technical effect, so that repetition is avoided, and details are not repeated herein.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the processes of the above-mentioned embodiment of the fault monitoring method of an access device, and can achieve the same technical effects, so that repetition is avoided, and no further description is given here. Wherein the computer readable storage medium is selected from Read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present invention.
The embodiments of the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present invention and the scope of the claims, which are to be protected by the present invention.
Claims (6)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463665.8A CN114630352B (en) | 2020-12-11 | 2020-12-11 | Fault monitoring method and device for access equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011463665.8A CN114630352B (en) | 2020-12-11 | 2020-12-11 | Fault monitoring method and device for access equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114630352A CN114630352A (en) | 2022-06-14 |
| CN114630352B true CN114630352B (en) | 2023-08-15 |
Family
ID=81894690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011463665.8A Active CN114630352B (en) | 2020-12-11 | 2020-12-11 | Fault monitoring method and device for access equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114630352B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115277491B (en) * | 2022-06-15 | 2023-06-06 | 中国联合网络通信集团有限公司 | Method, device, and computer-readable storage medium for determining abnormal data |
| CN115237040B (en) * | 2022-09-23 | 2022-12-16 | 河北东来工程技术服务有限公司 | Ship equipment safety operation management method, system, device and medium |
| CN115883325B (en) * | 2022-11-25 | 2025-07-25 | 国家电网有限公司信息通信分公司 | Network fault processing method, device, equipment and storage medium of power system |
| CN118484325A (en) * | 2023-02-10 | 2024-08-13 | 中兴通讯股份有限公司 | Method and device for acquiring cause and effect relationship and positioning root cause of system abnormality |
| CN115877269B (en) * | 2023-02-22 | 2023-05-09 | 深圳市胜威南方科技有限公司 | Power distribution early warning method, device, equipment and storage medium based on smart bus |
| CN116522138B (en) * | 2023-04-23 | 2025-11-11 | 哈尔滨工业大学 | Multi-element time sequence anomaly detection method and system based on weak supervision integration |
| CN117033160B (en) * | 2023-10-10 | 2024-01-19 | 中国电子信息产业集团有限公司第六研究所 | Method for predicting fault time of data acquisition equipment |
| CN117390468B (en) * | 2023-10-19 | 2024-06-04 | 应急管理部大数据中心 | Dust removal equipment state monitoring and early warning method and system based on data mining |
| CN117319179B (en) * | 2023-11-28 | 2024-06-21 | 中南大学 | Equipment abnormality monitoring method and system based on mechanism model and industrial Internet of Things |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2354945A1 (en) * | 2010-01-29 | 2011-08-10 | Honeywell International Inc. | Noisy monitor detection and intermittent fault isolation |
| CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
| CN104796277A (en) * | 2014-01-21 | 2015-07-22 | 中国移动通信集团湖南有限公司 | Network fault monitoring method and device |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN106201828A (en) * | 2016-07-18 | 2016-12-07 | 云南电网有限责任公司信息中心 | A kind of virtual-machine fail detection method based on data mining and system |
| CN108494594A (en) * | 2018-03-21 | 2018-09-04 | 中国人民解放军陆军炮兵防空兵学院郑州校区 | A kind of analysis method and system of EIGRP route networks failure |
| CN108491305A (en) * | 2018-03-09 | 2018-09-04 | 网宿科技股份有限公司 | A kind of detection method and system of server failure |
| WO2019028269A2 (en) * | 2017-08-02 | 2019-02-07 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for detection in an industrial internet of things data collection environment with large data sets |
| CN109376873A (en) * | 2018-09-11 | 2019-02-22 | 平安科技（深圳）有限公司 | O&M method, apparatus, electronic equipment and computer readable storage medium |
| CN109884475A (en) * | 2019-04-02 | 2019-06-14 | 云南电网有限责任公司大理供电局 | A kind of electric network fault detection method, device, system and storage medium |
| CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
| CN110224874A (en) * | 2019-06-27 | 2019-09-10 | 郑州阿帕斯科技有限公司 | A kind of processing method and processing device of equipment fault |
| 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 |
| CN111309539A (en) * | 2020-03-26 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Abnormity monitoring method and device and electronic equipment |
| CN111368890A (en) * | 2020-02-26 | 2020-07-03 | 珠海格力电器股份有限公司 | Fault detection method and device and information physical fusion system |
| CN111650922A (en) * | 2020-05-27 | 2020-09-11 | 北京金茂绿建科技有限公司 | Smart home abnormity detection method and device |
| CN111914320A (en) * | 2020-06-06 | 2020-11-10 | 同济大学 | Fault diagnosis method of no-sample switch based on deep learning |
-
2020
- 2020-12-11 CN CN202011463665.8A patent/CN114630352B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2354945A1 (en) * | 2010-01-29 | 2011-08-10 | Honeywell International Inc. | Noisy monitor detection and intermittent fault isolation |
| CN104796277A (en) * | 2014-01-21 | 2015-07-22 | 中国移动通信集团湖南有限公司 | Network fault monitoring method and device |
| CN104462846A (en) * | 2014-12-22 | 2015-03-25 | 山东鲁能软件技术有限公司 | Intelligent device failure diagnosis method based on support vector machine |
| CN105045256A (en) * | 2015-07-08 | 2015-11-11 | 北京泰乐德信息技术有限公司 | Rail traffic real-time fault diagnosis method and system based on data comparative analysis |
| CN106201828A (en) * | 2016-07-18 | 2016-12-07 | 云南电网有限责任公司信息中心 | A kind of virtual-machine fail detection method based on data mining and system |
| WO2019028269A2 (en) * | 2017-08-02 | 2019-02-07 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for detection in an industrial internet of things data collection environment with large data sets |
| CN108491305A (en) * | 2018-03-09 | 2018-09-04 | 网宿科技股份有限公司 | A kind of detection method and system of server failure |
| CN108494594A (en) * | 2018-03-21 | 2018-09-04 | 中国人民解放军陆军炮兵防空兵学院郑州校区 | A kind of analysis method and system of EIGRP route networks failure |
| CN109376873A (en) * | 2018-09-11 | 2019-02-22 | 平安科技（深圳）有限公司 | O&M method, apparatus, electronic equipment and computer readable storage medium |
| 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 |
| CN109884475A (en) * | 2019-04-02 | 2019-06-14 | 云南电网有限责任公司大理供电局 | A kind of electric network fault detection method, device, system and storage medium |
| CN110113226A (en) * | 2019-04-16 | 2019-08-09 | 新华三信息安全技术有限公司 | A kind of method and device of detection device exception |
| CN110224874A (en) * | 2019-06-27 | 2019-09-10 | 郑州阿帕斯科技有限公司 | A kind of processing method and processing device of equipment fault |
| CN111368890A (en) * | 2020-02-26 | 2020-07-03 | 珠海格力电器股份有限公司 | Fault detection method and device and information physical fusion system |
| CN111309539A (en) * | 2020-03-26 | 2020-06-19 | 北京奇艺世纪科技有限公司 | Abnormity monitoring method and device and electronic equipment |
| CN111650922A (en) * | 2020-05-27 | 2020-09-11 | 北京金茂绿建科技有限公司 | Smart home abnormity detection method and device |
| CN111914320A (en) * | 2020-06-06 | 2020-11-10 | 同济大学 | Fault diagnosis method of no-sample switch based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| A Case Study for Safety-Critical V2X Communications;Laurent Gallo;《IEEE XPLORE》;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114630352A (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114630352B (en) | Fault monitoring method and device for access equipment | |
| US20200134421A1 (en) | Assurance of policy based alerting | |
| US20160212023A1 (en) | Apparatus and method for processing data streams in a communication network | |
| CN111181971B (en) | System for automatically detecting industrial network attack | |
| CN116471196B (en) | Operation and maintenance monitoring network maintenance method, system and equipment | |
| CN118432710B (en) | Method for reporting fault of optical fiber communication link | |
| CN118631873B (en) | Data management system of internet of things platform based on cloud technology | |
| CN117914786A (en) | Smart IoT data processing method and management platform for cloud-edge collaboration | |
| CN113543188B (en) | Wireless network signal quality detection method, terminal equipment and storage medium | |
| CN119628874B (en) | A big data network signal security early warning system | |
| CN116032692B (en) | A smart Internet of Things gateway and an Internet of Things system based on the smart Internet of Things gateway | |
| CN119922250B (en) | Electronic information fusion transmission system supporting multiple protocols | |
| WO2024066331A1 (en) | Network abnormality detection method and apparatus, electronic device, and storage medium | |
| CN116980284B (en) | Optical cable fiber distribution box operation and maintenance information transmission method and system based on Internet of things | |
| CN114244691B (en) | Video service fault location method, device and electronic equipment | |
| CN116244765A (en) | A method for equipment maintenance and management based on industrial Internet | |
| CN119276710A (en) | Network quality optimization method, device, electronic device and storage medium | |
| CN120407549B (en) | Multi-level treatment method for real-time data of new energy station power generation equipment | |
| CN110708370A (en) | Data processing method and terminal | |
| CN118503051B (en) | A marketing system omni-channel unified access system | |
| CN110896544A (en) | Fault delimiting method and device | |
| CN119583329A (en) | A fault prediction method and system for IP network | |
| CN118827343A (en) | Method and system for locating and demarcating home broadband Internet access faults | |
| CN115426244B (en) | Network equipment fault detection method based on big data | |
| CN113055442B (en) | Event generation method based on dynamic factors, electronic 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 |