CN112492630A - Fault prediction method and device of base station equipment and base station - Google Patents
Fault prediction method and device of base station equipment and base station Download PDFInfo
- Publication number
- CN112492630A CN112492630A CN201910855337.3A CN201910855337A CN112492630A CN 112492630 A CN112492630 A CN 112492630A CN 201910855337 A CN201910855337 A CN 201910855337A CN 112492630 A CN112492630 A CN 112492630A
- Authority
- CN
- China
- Prior art keywords
- prediction
- failure
- fault
- base station
- prediction result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- 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
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W88/00—Devices specially adapted for wireless communication networks, e.g. terminals, base stations or access point devices
- H04W88/08—Access point devices
Abstract
The disclosure relates to a fault prediction method and device of base station equipment and a base station, and relates to the technical field of communication. The method comprises the following steps: performing fault prediction by using a machine learning method according to working operation parameters of base station equipment to determine a plurality of first prediction results, wherein the first prediction results comprise at least one fault attribute; according to the hardware attribute parameters of the base station equipment, performing fault prediction by using a machine learning method to determine a plurality of second prediction results, wherein the second prediction results comprise the same type of fault attributes as the first prediction results; screening out a first prediction result and a second prediction result with the same numerical value of the fault attribute, and determining the first prediction result as a first fault comprehensive prediction result of the base station equipment.
Description
Technical Field
The present disclosure relates to the field of communications technologies, and in particular, to a method for predicting a failure of a base station device, a device for predicting a failure of a base station device, a base station, and a computer-readable storage medium.
Background
The 4G radio Base station equipment is composed of a BBU (Base Band Unit) and an RRU (Remote RF Unit). Communication between the BBU and the RRU of the Radio base station is connected by a Common Public Radio Interface (CPRI) optical fiber through an Interface between the BBU and the RRU.
In a scenario where RRU is remote, a failure of link interruption due to aging of an optical fiber and a connector often occurs. Therefore, a certain failure rate occurs in this section of optical path, and if the optical path is not processed in time, the network index is seriously affected, and even the problems of station break and service break occur. In order to ensure the normal operation of the base station equipment, improve network indexes, predict the faults of the base station equipment and remove the faults in advance, it is imperative.
In the related technology, the problems of joint looseness, line aging and the like which possibly occur are checked in a manual inspection mode, and devices are replaced in time. Or after the fault occurs, professional operation and maintenance personnel locate the fault through the alarm information by depending on experience to solve the fault.
Disclosure of Invention
The inventors of the present disclosure found that the following problems exist in the above-described related art: the fault processing efficiency is low due to the fact that manual experience is used for troubleshooting after the fault occurs.
In view of this, the present disclosure provides a technical solution for predicting a failure of a base station device, which can improve failure processing efficiency.
According to some embodiments of the present disclosure, there is provided a failure prediction method of a base station device, including: performing fault prediction by using a machine learning method according to working operation parameters of base station equipment to determine a plurality of first prediction results, wherein the first prediction results comprise at least one fault attribute; performing fault prediction by using a machine learning method according to the hardware attribute parameters of the base station equipment to determine a plurality of second prediction results, wherein the second prediction results comprise fault attributes of the same type as the first prediction results; and screening the first prediction result and the second prediction result with the same numerical value of the fault attribute, and determining the first prediction result and the second prediction result as a first fault comprehensive prediction result of the base station equipment.
In some embodiments, the failure prediction method further includes: according to the fault attributes, clustering the first prediction result and the second prediction result except the first fault comprehensive prediction result; and determining the first prediction result and the second prediction result of which the processing results are the same type as a second failure comprehensive prediction result of the base station equipment, wherein the failure probability of the second failure comprehensive prediction result is lower than that of the first failure comprehensive prediction result.
In some embodiments, the failure prediction method further includes: and determining the first prediction result and the second prediction result of which the processing results are not in the same class as a third fault comprehensive prediction result of the base station equipment, wherein the fault possibility of the third fault comprehensive prediction result is lower than that of the second fault comprehensive prediction result.
In some embodiments, before performing the fault prediction, the fault prediction method further includes: and respectively carrying out sequence anomaly detection processing on the working operation parameters and the hardware attribute parameters according to the data statistical characteristics of the working operation parameters and the hardware attribute parameters to obtain the processed working operation parameters and the processed hardware attribute parameters.
In some embodiments, the operational operating parameter comprises at least one of a received power, a transmitted power, a temperature, a bias current, a voltage, a bit error rate of the base station device; the hardware attribute parameters include at least one of a date of manufacture, a number of years of use, a recommended age, and failure history information of the base station apparatus.
In some embodiments, the fault attributes include at least one of a base station number, a base station equipment number, a fault occurrence device or interface, a fault category, and a fault occurrence time.
In some embodiments, the type of the operating parameter is determined according to historical fault warning information of the base station equipment and corresponding fault classification.
According to other embodiments of the present disclosure, there is provided a failure prediction apparatus of a base station device, including: the prediction unit is used for performing fault prediction by using a machine learning method according to working operation parameters of base station equipment to determine a plurality of first prediction results, wherein the first prediction results comprise at least one fault attribute, and performing fault prediction by using the machine learning method according to hardware attribute parameters of the base station equipment to determine a plurality of second prediction results, wherein the second prediction results comprise the same type of fault attributes as the first prediction results; and the determining unit is used for screening out the first prediction result and the second prediction result with the same numerical value of the fault attribute and determining the first prediction result as the first fault comprehensive prediction result of the base station equipment.
In some embodiments, the determining unit performs clustering processing on the first prediction result and the second prediction result except for the first failure comprehensive prediction result according to the failure attribute, and determines the first prediction result and the second prediction result whose processing results are of the same class as the second failure comprehensive prediction result of the base station device, where the failure probability of the second failure comprehensive prediction result is lower than that of the first failure comprehensive prediction result.
In some embodiments, the determining unit determines, as the third failure comprehensive prediction result of the base station device, the first prediction result and the second prediction result whose processing results are not of the same class, where the failure probability of the third failure comprehensive prediction result is lower than that of the second failure comprehensive prediction result.
In some embodiments, the failure prediction apparatus further includes: and the detection processing unit is used for respectively carrying out sequence anomaly detection processing on the working operation parameters and the hardware attribute parameters according to the data statistical characteristics of the working operation parameters and the hardware attribute parameters to obtain the processed working operation parameters and the processed hardware attribute parameters.
In some embodiments, the operational operating parameter comprises at least one of a received power, a transmitted power, a temperature, a bias current, a voltage, a bit error rate of the base station device; the hardware attribute parameters include at least one of a date of manufacture, a number of years of use, a recommended age, and failure history information of the base station apparatus.
In some embodiments, the fault attributes include at least one of a base station number, a base station equipment number, a fault occurrence device or interface, a fault category, and a fault occurrence time.
In some embodiments, the type of the operating parameter is determined according to historical fault warning information of the base station equipment and corresponding fault classification.
According to still other embodiments of the present disclosure, there is provided a failure prediction apparatus of a base station device, including: a memory; and a processor coupled to the memory, the processor configured to perform the method of failure prediction of a base station device in any of the above embodiments based on instructions stored in the memory device.
According to still further embodiments of the present disclosure, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a failure prediction method of a base station apparatus in any of the above embodiments.
According to still further embodiments of the present disclosure, there is provided a base station including: the failure prediction apparatus of a base station device according to any of the above embodiments.
In the embodiment, the fault prediction is performed by adopting a machine learning method from two aspects of the operation parameters and the hardware parameters, and the comprehensive prediction result is determined by combining the prediction results of the two aspects. Thus, automatic failure prediction can be performed in many ways before a failure occurs, thereby improving the efficiency of failure processing.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
fig. 1 illustrates a flow diagram of some embodiments of a method of fault prediction for a base station apparatus of the present disclosure;
fig. 2 shows a flow diagram of further embodiments of a method of fault prediction for a base station apparatus of the present disclosure;
fig. 3 shows a schematic diagram of some embodiments of a failure prediction method of a base station apparatus of the present disclosure;
fig. 4 shows a schematic diagram of further embodiments of a method of failure prediction of a base station apparatus of the present disclosure;
fig. 5 shows a schematic diagram of some embodiments of a failure prediction apparatus of a base station device of the present disclosure;
fig. 6 shows a block diagram of further embodiments of a failure prediction apparatus of a base station arrangement of the present disclosure;
fig. 7 shows a block diagram of further embodiments of a failure prediction apparatus of a base station device of the present disclosure;
fig. 8 illustrates a block diagram of some embodiments of a base station of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Fig. 1 shows a flow chart of some embodiments of a method of fault prediction of a base station apparatus of the present disclosure.
As shown in fig. 1, the method includes: step 110, predicting a fault according to the working operation parameters; step 120, predicting faults according to the hardware attribute parameters; and step 130, determining a first failure comprehensive prediction result.
In step 110, a machine learning method is used to perform fault prediction based on the operating parameters of the base station device to determine a plurality of first prediction results. The first prediction result includes at least one fault attribute.
In some embodiments, the type of the operating parameter that may cause the failure of the base station device may be determined by analyzing information such as historical failure alarm information and failure classification of the base station. For example, fault classification may include: the method comprises the following steps of RRU single board failure, optical module unavailability, optical module out of place, optical port transmitting or receiving link failure and the like. Relevant operating parameters may be determined based on information such as fault classification (e.g., via machine learning methods). The operational operating parameters may include at least one of received power, transmit power, temperature, bias current, voltage, bit error rate of the base station device.
In some embodiments, the machine learning method may be an artificial intelligence fault prediction algorithm such as a support vector machine, a decision tree, a random forest, and the like. The failure prediction can be performed from an operation perspective by processing the working operation parameters by a machine learning method, so that a plurality of first prediction results are obtained. For example, the plurality of first predictors may form a failure predictor set a.
In some embodiments, each first prediction may have at least one fault attribute as an attribute. For example, the fault attribute may include at least one of a base station number, a base station equipment number, a fault occurrence device or interface, a fault category, and a fault occurrence time.
In step 120, a machine learning method is used to perform fault prediction according to the hardware attribute parameters of the base station device to determine a plurality of second prediction results, where the second prediction results include the same type of fault attributes as the first prediction results.
In some embodiments, the base station device may be a BBU, an RRU, an optical module, a power supply, an antenna, a connection line, and the like. For example, the hardware attribute parameter may include at least one of a production date, a number of years of use, a recommended period of use, and failure history information of the base station device.
In some embodiments, processing the hardware attribute parameters using a machine learning method may perform fault prediction from a hardware perspective, resulting in a plurality of second prediction results. For example, the plurality of second predictors may form a failure predictor set B. The second predicted outcome includes the same type of fault attribute as the first predicted outcome for comparison with the first predicted outcome.
In some embodiments, before the fault prediction is performed, the working operation parameters and the hardware attribute parameters may be subjected to data cleaning, and then processed by using a correlation method of feature engineering, so as to obtain an appropriate data model for the fault prediction.
For example, according to the data statistical characteristics of the working operation parameters and the hardware attribute parameters, sequence anomaly detection processing can be performed on the working operation parameters and the hardware attribute parameters respectively, so that the processed working operation parameters and the processed hardware attribute parameters are used for fault prediction. For example, the data statistics may include one or more of mean, variance, quartile, and steep drop point.
Therefore, the feature model obtained by processing the working operation parameters and the hardware attribute parameters in a mode of combining a plurality of feature expression processing methods is beneficial to improving the accuracy of prediction.
In step 130, the first prediction result and the second prediction result with the same value of the fault attribute are screened out and determined as the first fault comprehensive prediction result of the base station device.
In some embodiments, a coincidence detection may be performed on a first predictor in the failure predictor set a and a second predictor in the failure predictor set B. For example, whether the first prediction result and the second prediction result occur in the same time period and other failure attributes are the same (i.e., coincidence detection conditions) may be determined by the failure attribute; in the case of yes, the corresponding first prediction result and second prediction result are determined as the first failure comprehensive prediction result, namely the failure with the highest prediction possibility and the most urgent failure.
In some embodiments, after the most probable and most urgent fault is determined by the coincidence degree, other fault prediction results may be processed by the similarity determination, so as to further determine the probability of the fault prediction result. This may be achieved, for example, by the embodiment of fig. 2.
Fig. 2 shows a flow chart of further embodiments of a method of failure prediction of a base station apparatus of the present disclosure.
As shown in fig. 2, compared to the method in the embodiment in fig. 1, the present embodiment may further include: step 210, clustering; and step 220, determining a second failure comprehensive prediction result.
In step 210, a first prediction result and a second prediction result other than the first failure comprehensive prediction result are clustered according to the failure attribute.
In step 220, the processing result is the first prediction result and the second prediction result of the same type, and is determined as the second failure comprehensive prediction result of the base station device, and the failure probability of the second failure comprehensive prediction result is lower than that of the first failure comprehensive prediction result.
In some embodiments, similarity detection may be performed on a first prediction result and a second prediction result which are assumed as a first failure comprehensive prediction result in the failure prediction result set a and the failure prediction result set B.
For example, the prediction results other than the first failure comprehensive prediction result in the failure prediction result set a and the failure prediction result set B may be processed by a cluster analysis method. Determining a first prediction result and a second prediction result which occur in the same time period and have similar fault attributes as a second fault comprehensive prediction result (namely, the second fault comprehensive prediction result meets the similarity detection condition), namely, a fault which has a high prediction possibility and is the second most urgent fault; and determining the first prediction result and the second prediction result which do not occur in the same time period and have dissimilar fault attributes as a third fault comprehensive prediction result, namely, the fault with low prediction possibility and lowest emergency.
In some embodiments, a failure that may occur in the IR light path of the base station over a period of time may be predicted by the method in any of the embodiments described above. According to the characteristics of the base station, the predicted results from the aspects of operation and hardware can be mutually supported. Moreover, the prediction accuracy can be improved through fault classification, and reasonable suggestions are provided for processing priorities.
Fig. 3 shows a schematic diagram of some embodiments of a failure prediction method of a base station apparatus of the present disclosure.
As shown in fig. 3, a historical failure of the base station device may be analyzed first to determine a working operation parameter that may cause the failure; then, preprocessing the working operation parameters and detecting and processing the sequence abnormity based on the data statistical characteristics; and performing fault prediction based on the processed working operation parameters to obtain a fault prediction result set A.
The hardware attribute parameters of the base station equipment can be preprocessed and sequence anomaly detection processing based on data statistical characteristics can be carried out; and performing fault prediction based on the processed hardware attribute parameters to obtain a fault prediction result set B.
The overlap ratio detection in any of the above embodiments may be used to process the elements in the failure prediction result set a and the failure prediction result set B; and the faults meeting the coincidence degree detection judgment condition are taken as a type of fault (namely a first fault comprehensive prediction result).
The similarity detection processing in any one of the embodiments described above may be performed on elements in the failure prediction result set a and the failure prediction result set B that do not meet the overlap ratio detection condition; the faults meeting the similarity detection condition are taken as second-class faults (namely second fault comprehensive prediction results); and the faults which do not meet the similarity detection condition are taken as three types of faults (namely, third fault comprehensive prediction results).
Fig. 4 shows a schematic diagram of further embodiments of a method of failure prediction of a base station apparatus of the present disclosure.
As shown in fig. 4, a system adopting the fault prediction method for the base station device may be divided into an interactive interface, a core control module, a data processing module, a database module, a data acquisition module, and the like.
The interactive interface module can be used for carrying out an information interaction interface for a user, visually presenting a prediction result, and feeding back required information by the user.
The core control module can complete the base station IR light path fault prediction through a detection module and an algorithm model (such as a decision tree model); the feedback module feeds back and corrects the self-learning function; and allocating required logic and data relation, fault detection algorithm of different data and fault detection grading condition through the functional interface.
The data processing module can respectively carry out data cleaning on the working operation parameters and the hardware attribute parameters of the database module; and a specified data model to be processed is generated by a feature engineering module by using a proper mixed feature engineering method (such as sequence anomaly detection, a quartile method, a steep drop point method and the like).
The database module stores the work operation parameters and the hardware attribute parameters acquired by the wireless base station.
The data acquisition module can acquire information such as working operation parameters, hardware attribute parameters, alarm data, service states and the like generated by BBUs, RRUs and optical interface equipment of different wireless base stations at different daily time periods.
In the embodiment, the existing method for manual troubleshooting after a fault occurs is broken through, prediction is performed from two aspects of operation and hardware through an artificial intelligence algorithm, the prediction capability before the fault is realized, and the network stability is guaranteed.
And selecting a proper machine learning algorithm (random forest algorithm and the like) according to the alarm historical data of the base station to construct a fault prediction model. The working operation parameters are processed by selecting mean value, variance, quartile and steep drop points and then carrying out sequence anomaly detection based on feature expression. Therefore, the data model to be processed is obtained by combining a plurality of characteristic expression processing methods.
According to the prediction results of the operation and hardware angles, the comprehensive fault prediction results are classified by using the fault grading conditions of the contact ratio and the similarity, the prediction accuracy is ensured, and the emergency of the fault is cleared.
A set of presentation device for fault prediction is constructed, and the result of system prediction is presented on a front-end interface, so that professional manual later maintenance and fault information correction are facilitated.
In the embodiment, the fault prediction is performed by adopting a machine learning method from two aspects of the operation parameters and the hardware parameters, and the comprehensive prediction result is determined by combining the prediction results of the two aspects. Thus, automatic failure prediction can be performed in many ways before a failure occurs, thereby improving the efficiency of failure processing.
Fig. 5 shows a schematic diagram of some embodiments of a failure prediction apparatus of a base station device of the present disclosure.
As shown in fig. 5, the failure prediction device 5 of the base station apparatus includes a prediction unit 51 and a determination unit 52.
The prediction unit 51 performs failure prediction using a machine learning method based on the operating parameters of the base station apparatus to determine a plurality of first prediction results. The first prediction result comprises at least one fault attribute; the prediction unit 51 performs failure prediction using a machine learning method based on the hardware attribute parameters of the base station device to determine a plurality of second prediction results. The second prediction result comprises the same type of fault attributes of the first prediction result. For example, the fault attribute includes at least one of a base station number, a base station equipment number, a fault occurrence device or interface, a fault category, and a fault occurrence time.
In some embodiments, the type of the operating parameter is determined according to historical fault warning information of the base station equipment and corresponding fault classification. For example, the operational operating parameter includes at least one of a received power, a transmit power, a temperature, a bias current, a voltage, and a bit error rate of the base station device.
In some embodiments, the hardware attribute parameters include at least one of a date of manufacture, a number of years of use, a recommended age, and failure history information of the base station device.
The determining unit 52 screens out the first prediction result and the second prediction result having the same value of the fault attribute, and determines the first prediction result as the first fault comprehensive prediction result of the base station device.
In some embodiments, the determining unit 52 performs clustering processing on the first prediction result and the second prediction result other than the first failure comprehensive prediction result according to the failed attribute; the determination unit 52 determines the first prediction result and the second prediction result, of which the processing results are the same type, as the second failure comprehensive prediction result of the base station apparatus. The second failure comprehensive prediction result has a lower failure probability than the first failure comprehensive prediction result.
In some embodiments, the determination unit 52 determines the first prediction result and the second prediction result, of which the processing results are not of the same class, as the third failure comprehensive prediction result of the base station apparatus. The failure probability of the third failure comprehensive prediction result is lower than that of the second failure comprehensive prediction result.
In some embodiments, the failure prediction apparatus further includes a detection processing unit 53, configured to perform sequence anomaly detection processing on the working operation parameter and the hardware attribute parameter respectively according to data statistical characteristics of the working operation parameter and the hardware attribute parameter, so as to obtain a processed working operation parameter and a processed hardware attribute parameter.
In the embodiment, the fault prediction is performed by adopting a machine learning method from two aspects of the operation parameters and the hardware parameters, and the comprehensive prediction result is determined by combining the prediction results of the two aspects. Thus, automatic failure prediction can be performed in many ways before a failure occurs, thereby improving the efficiency of failure processing.
Fig. 6 shows a block diagram of further embodiments of a failure prediction apparatus of a base station device of the present disclosure.
As shown in fig. 6, the failure prediction apparatus 6 of the base station device of the embodiment includes: a memory 61 and a processor 62 coupled to the memory 61, the processor 62 being configured to execute a method of failure prediction of a base station device in any one of the embodiments of the present disclosure based on instructions stored in the memory 61.
The memory 61 may include, for example, a system memory, a fixed nonvolatile storage medium, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), a database, and other programs.
Fig. 7 shows a block diagram of further embodiments of the failure prediction apparatus of the base station device of the present disclosure.
As shown in fig. 7, the failure prediction apparatus 7 of the base station device of this embodiment includes: a memory 710 and a processor 720 coupled to the memory 710, the processor 720 being configured to execute the method for predicting a failure of a base station device in any of the foregoing embodiments based on instructions stored in the memory 710.
The memory 710 may include, for example, system memory, fixed non-volatile storage media, and the like. The system memory stores, for example, an operating system, an application program, a Boot Loader (Boot Loader), and other programs.
The failure prediction means 7 of the base station apparatus may further include an input-output interface 730, a network interface 740, a storage interface 750, and the like. These interfaces 730, 740, 750, as well as the memory 710 and the processor 720, may be connected, for example, by a bus 760. The input/output interface 730 provides a connection interface for input/output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 740 provides a connection interface for various networking devices. The storage interface 750 provides a connection interface for external storage devices such as an SD card and a usb disk.
Fig. 8 illustrates a block diagram of some embodiments of a base station of the present disclosure.
As shown in fig. 8, the base station 8 includes the failure prediction means 81 of the base station apparatus in any of the embodiments described above.
As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, system, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
So far, the failure prediction method of the base station apparatus, the failure prediction device of the base station apparatus, the base station, and the computer-readable storage medium according to the present disclosure have been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the foregoing examples are for purposes of illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications may be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (14)
1. A failure prediction method of a base station device includes:
performing fault prediction by using a machine learning method according to working operation parameters of base station equipment to determine a plurality of first prediction results, wherein the first prediction results comprise at least one fault attribute;
performing fault prediction by using a machine learning method according to the hardware attribute parameters of the base station equipment to determine a plurality of second prediction results, wherein the second prediction results comprise fault attributes of the same type as the first prediction results;
and screening the first prediction result and the second prediction result with the same numerical value of the fault attribute, and determining the first prediction result and the second prediction result as a first fault comprehensive prediction result of the base station equipment.
2. The failure prediction method of claim 1, further comprising:
according to the fault attributes, clustering the first prediction result and the second prediction result except the first fault comprehensive prediction result;
and determining the first prediction result and the second prediction result of which the processing results are the same type as a second failure comprehensive prediction result of the base station equipment, wherein the failure probability of the second failure comprehensive prediction result is lower than that of the first failure comprehensive prediction result.
3. The failure prediction method of claim 2, further comprising:
and determining the first prediction result and the second prediction result of which the processing results are not in the same class as a third fault comprehensive prediction result of the base station equipment, wherein the fault possibility of the third fault comprehensive prediction result is lower than that of the second fault comprehensive prediction result.
4. The failure prediction method of claim 1, further comprising, prior to performing failure prediction:
and respectively carrying out sequence anomaly detection processing on the working operation parameters and the hardware attribute parameters according to the data statistical characteristics of the working operation parameters and the hardware attribute parameters to obtain the processed working operation parameters and the processed hardware attribute parameters.
5. The failure prediction method according to any one of claims 1 to 4,
the working operation parameters comprise at least one of receiving power, transmitting power, temperature, bias current, voltage and bit error rate of the base station equipment;
the hardware attribute parameters include at least one of a date of manufacture, a number of years of use, a recommended age, and failure history information of the base station apparatus.
6. The failure prediction method according to any one of claims 1 to 4,
the fault attribute comprises at least one of a base station number, a base station equipment number, a fault generation device or interface, a fault type and a fault generation time.
7. The failure prediction method according to any one of claims 1 to 4,
and the type of the working operation parameter is determined according to the historical fault warning information of the base station equipment and the corresponding fault classification.
8. A failure prediction apparatus of a base station device, comprising:
the prediction unit is used for performing fault prediction by using a machine learning method according to working operation parameters of base station equipment to determine a plurality of first prediction results, wherein the first prediction results comprise at least one fault attribute, and performing fault prediction by using the machine learning method according to hardware attribute parameters of the base station equipment to determine a plurality of second prediction results, wherein the second prediction results comprise the same type of fault attributes as the first prediction results;
and the determining unit is used for screening out the first prediction result and the second prediction result with the same numerical value of the fault attribute and determining the first prediction result as the first fault comprehensive prediction result of the base station equipment.
9. The failure prediction apparatus of claim 8,
the determining unit performs clustering processing on the first prediction result and the second prediction result except the first failure comprehensive prediction result according to the failure attribute, and determines the first prediction result and the second prediction result of which the processing results are of the same type as a second failure comprehensive prediction result of the base station equipment, wherein the failure probability of the second failure comprehensive prediction result is lower than that of the first failure comprehensive prediction result.
10. The failure prediction apparatus of claim 9,
the determining unit determines the first prediction result and the second prediction result, of which processing results are not of the same class, as a third failure comprehensive prediction result of the base station device, where the failure probability of the third failure comprehensive prediction result is lower than that of the second failure comprehensive prediction result.
11. The failure prediction device of claim 8, further comprising:
and the detection processing unit is used for respectively carrying out sequence anomaly detection processing on the working operation parameters and the hardware attribute parameters according to the data statistical characteristics of the working operation parameters and the hardware attribute parameters to obtain the processed working operation parameters and the processed hardware attribute parameters.
12. A failure prediction apparatus of a base station device, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of fault prediction of a base station apparatus of any of claims 1-7 based on instructions stored in the memory device.
13. A computer-readable storage medium on which a computer program is stored, which when executed by a processor, implements the failure prediction method of the base station apparatus of any one of claims 1 to 7.
14. A base station, comprising:
a failure prediction apparatus of a base station device as claimed in any one of claims 8 to 12.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910855337.3A CN112492630B (en) | 2019-09-11 | 2019-09-11 | Fault prediction method and device of base station equipment and base station |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910855337.3A CN112492630B (en) | 2019-09-11 | 2019-09-11 | Fault prediction method and device of base station equipment and base station |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112492630A true CN112492630A (en) | 2021-03-12 |
CN112492630B CN112492630B (en) | 2023-02-03 |
Family
ID=74919791
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910855337.3A Active CN112492630B (en) | 2019-09-11 | 2019-09-11 | Fault prediction method and device of base station equipment and base station |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112492630B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115037599A (en) * | 2022-06-13 | 2022-09-09 | 中国电信股份有限公司 | Communication network fault early warning method, device, equipment and medium |
CN115334560A (en) * | 2022-08-19 | 2022-11-11 | 中国联合网络通信集团有限公司 | Method, device and equipment for monitoring base station abnormity and computer readable storage medium |
WO2024078135A1 (en) * | 2022-10-12 | 2024-04-18 | 中兴通讯股份有限公司 | Topological networking identification method and apparatus, and electronic device and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
CN108664010A (en) * | 2018-05-07 | 2018-10-16 | 广东省电信规划设计院有限公司 | Generating set fault data prediction technique, device and computer equipment |
US20190095313A1 (en) * | 2017-09-22 | 2019-03-28 | Nec Laboratories America, Inc. | Log-based system maintenance and management |
CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
CN109738782A (en) * | 2018-12-07 | 2019-05-10 | 上海交通大学 | Board failure detection method and system based on measurement data machine learning |
-
2019
- 2019-09-11 CN CN201910855337.3A patent/CN112492630B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107016404A (en) * | 2017-02-24 | 2017-08-04 | 沈阳工业大学 | Wind power generating set failure prediction method based on D S evidence fusions |
US20190095313A1 (en) * | 2017-09-22 | 2019-03-28 | Nec Laboratories America, Inc. | Log-based system maintenance and management |
CN108664010A (en) * | 2018-05-07 | 2018-10-16 | 广东省电信规划设计院有限公司 | Generating set fault data prediction technique, device and computer equipment |
CN109738782A (en) * | 2018-12-07 | 2019-05-10 | 上海交通大学 | Board failure detection method and system based on measurement data machine learning |
CN109634828A (en) * | 2018-12-17 | 2019-04-16 | 浪潮电子信息产业股份有限公司 | Failure prediction method, device, equipment and storage medium |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115037599A (en) * | 2022-06-13 | 2022-09-09 | 中国电信股份有限公司 | Communication network fault early warning method, device, equipment and medium |
CN115334560A (en) * | 2022-08-19 | 2022-11-11 | 中国联合网络通信集团有限公司 | Method, device and equipment for monitoring base station abnormity and computer readable storage medium |
CN115334560B (en) * | 2022-08-19 | 2024-05-07 | 中国联合网络通信集团有限公司 | Base station abnormality monitoring method, device, equipment and computer readable storage medium |
WO2024078135A1 (en) * | 2022-10-12 | 2024-04-18 | 中兴通讯股份有限公司 | Topological networking identification method and apparatus, and electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN112492630B (en) | 2023-02-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112492630B (en) | Fault prediction method and device of base station equipment and base station | |
EP3975048A1 (en) | Method for constructing cloud network alarm root cause relational tree model, device, and storage medium | |
EP2871803B1 (en) | Network node failure predictive system | |
US20170364819A1 (en) | Root cause analysis in a communication network via probabilistic network structure | |
CN111126824A (en) | Multi-index association model training method and multi-index anomaly analysis method | |
WO2017041406A1 (en) | Failure positioning method and device | |
AU2016213726A1 (en) | Core network analytics system | |
US11586981B2 (en) | Failure analysis device, failure analysis method, and failure analysis program | |
CN110674009B (en) | Application server performance monitoring method and device, storage medium and electronic equipment | |
US11757701B2 (en) | Method for recommending similar incident, and related device | |
CN105116870A (en) | Fault analysis method, device and system of air conditioning unit | |
CN115033463B (en) | System exception type determining method, device, equipment and storage medium | |
CN117395695A (en) | On-line diagnosis processing system for wireless network | |
US8897167B2 (en) | Diversity monitoring for communication network circuits | |
CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
CN113760634A (en) | Data processing method and device | |
Rozaki | Network fault diagnosis using data mining classifiers | |
EP3833089A1 (en) | Automated narrow peak interference severity estimation | |
CN115348147A (en) | Fault analysis method, apparatus, device, storage medium and program product | |
CN113328898A (en) | Fault diagnosis method and system with autonomous learning capability | |
CN111861021A (en) | Business risk prediction method, device, equipment and computer readable storage medium | |
CN112015627A (en) | Data acquisition method and related device | |
CN114363194B (en) | Hidden danger analysis method and device for network equipment, electronic equipment and storage medium | |
CN117792864A (en) | Alarm processing method and device, storage medium and electronic device | |
US20230047057A1 (en) | Automatically using configuration management analytics in cellular networks |
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 |