CN112367678A - Micro base station monitoring method and device and storage medium - Google Patents
Micro base station monitoring method and device and storage medium Download PDFInfo
- Publication number
- CN112367678A CN112367678A CN202011100600.7A CN202011100600A CN112367678A CN 112367678 A CN112367678 A CN 112367678A CN 202011100600 A CN202011100600 A CN 202011100600A CN 112367678 A CN112367678 A CN 112367678A
- Authority
- CN
- China
- Prior art keywords
- information
- monitoring
- base station
- alarm
- training
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 108
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims description 70
- 238000012545 processing Methods 0.000 claims description 28
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 18
- 238000010801 machine learning Methods 0.000 claims description 16
- 238000010606 normalization Methods 0.000 claims description 14
- 238000010438 heat treatment Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 7
- 238000011084 recovery Methods 0.000 abstract description 3
- 238000013024 troubleshooting Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 230000015654 memory Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 230000002452 interceptive effect Effects 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 230000006855 networking Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 230000011664 signaling Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005057 refrigeration Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000344 soap Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a micro base station monitoring method and device and a storage medium, wherein the method comprises the following steps: acquiring operation information of the micro base station; classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information; inputting alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result; and sending the fault alarm prediction result and the equipment off-network prediction result to a monitoring center. Because the operation information of the micro base station is classified, and then deep learning is carried out on the operation information of different types, faults can be accurately predicted, off-network equipment can be accurately predicted, the working difficulty of operation and maintenance personnel of the micro base station is effectively reduced, and more accurate state monitoring, fault troubleshooting and self-recovery are provided.
Description
Technical Field
The invention relates to the technical field of base station communication, in particular to a micro base station monitoring method and device and a storage medium.
Background
With the development of 5G, the coverage area of a single base station becomes smaller, the penetration capability of signals is weakened, and attenuation of outdoor signals after arriving indoors is very serious, so that outdoor high-frequency base stations are difficult to effectively cover indoors, and indoor communication is inevitably unsmooth. Therefore, more micro base station access points are needed to deploy 5G. Meanwhile, the density of the micro base station building is high, the networking mode is diversified, and the macro base station and the micro base station are required to be subjected to three-dimensional networking in more application scenes in the future. Therefore, the deployment of indoor micro base stations will become a "position" for the future key competition of large operators.
One of the main functions of the micro base station is 'blind patching', and the micro base station can cover a population dense area which cannot be accurately reached by a macro base station, and incidentally solves the problem of difficult address selection of the macro base station. The micro base station is used as the bottom layer network support of the interconnection of everything by the characteristics of high flexibility, easy deployment and controllability, and can certainly realize large-scale increase of the quantity in the near future. Therefore, the monitoring and normal operation and maintenance of the micro base station equipment are challenged, and the micro base station is more difficult to maintain due to the fact that the micro base station is more influenced by the difficulty of indoor personnel entering, the autonomous behaviors of a network and a user and the like. Therefore, the traditional network management mode is no longer suitable for the monitoring requirement of the micro base station, more and more micro base stations and a large amount of alarm information make troubleshooting and positioning of faults more difficult. If a plurality of faults are concurrent, the situation is more complicated and difficult to describe, and operation and maintenance personnel are often difficult to rapidly troubleshoot and solve the faults when facing massive alarm information.
Under the circumstances, a new monitoring system is needed to be provided, so that the accuracy of the alarm is more intelligently improved, and the system is automatically restored as much as possible, the base station is operated and maintained in a reliable scheme, and the maintenance difficulty of operation and maintenance personnel is effectively reduced.
Disclosure of Invention
The invention mainly solves the technical problem of how to more effectively monitor the micro base station.
According to a first aspect, an embodiment provides a micro base station monitoring method, including:
acquiring operation information of the micro base station;
classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information;
inputting the alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result;
and sending the fault alarm prediction result and the equipment off-network prediction result to a monitoring center.
According to a second aspect, an embodiment provides a micro base station monitoring apparatus, including:
the base station monitoring unit is used for acquiring the operation information of the micro base station;
the data classification unit is used for classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information;
the data prediction unit is used for inputting the alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result;
and the result monitoring unit is used for sending the fault alarm prediction result and the equipment off-network prediction result to a monitoring center.
According to a third aspect, an embodiment provides a computer-readable storage medium comprising a program executable by a processor to implement the method of the above-described embodiment.
According to the monitoring method/device for the micro base station, the operation information of the micro base station is classified, and then deep learning is performed according to different types of operation information, so that faults and off-network equipment can be accurately predicted, the working difficulty of operation and maintenance personnel of the micro base station is effectively reduced, and more accurate state monitoring, fault troubleshooting and self recovery are provided.
Drawings
Fig. 1 is a flowchart of a micro base station monitoring method according to an embodiment;
fig. 2 is a block diagram of a micro base station monitoring apparatus according to an embodiment;
fig. 3 is a block diagram of a micro base station monitoring service architecture.
Detailed Description
The present invention will be described in further detail with reference to the following detailed description and accompanying drawings. Wherein like elements in different embodiments are numbered with like associated elements. In the following description, numerous details are set forth in order to provide a better understanding of the present application. However, those skilled in the art will readily recognize that some of the features may be omitted or replaced with other elements, materials, methods in different instances. In some instances, certain operations related to the present application have not been shown or described in detail in order to avoid obscuring the core of the present application from excessive description, and it is not necessary for those skilled in the art to describe these operations in detail, so that they may be fully understood from the description in the specification and the general knowledge in the art.
Furthermore, the features, operations, or characteristics described in the specification may be combined in any suitable manner to form various embodiments. Also, the various steps or actions in the method descriptions may be transposed or transposed in order, as will be apparent to one of ordinary skill in the art. Thus, the various sequences in the specification and drawings are for the purpose of describing certain embodiments only and are not intended to imply a required sequence unless otherwise indicated where such sequence must be followed.
The numbering of the components as such, e.g., "first", "second", etc., is used herein only to distinguish the objects as described, and does not have any sequential or technical meaning. The term "connected" and "coupled" when used in this application, unless otherwise indicated, includes both direct and indirect connections (couplings).
Referring to fig. 1, fig. 1 is a flowchart illustrating a micro base station monitoring method according to an embodiment, where the method includes steps S10 to S40, which are described in detail below.
And step S10, acquiring the operation information of the micro base station. The embodiment acquires the operation information of the micro base station through the monitoring unit FSU.
And step S20, classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information. The alarm information comprises alarm information generated on hardware and software of the micro base station equipment; the control information comprises signaling data, interactive data, configuration data of the micro base station, the monitoring unit FSU and the equipment mounted by the micro base station and the monitoring unit FSU; the monitoring information includes all available data on the base station device, such as operating parameters and states of the system, debugging and warning information of software, service data, and the like.
Step S30, inputting the alarm information into a pre-constructed automatic alarm recognition model to obtain a fault alarm prediction result; and inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result.
And step S40, sending the failure alarm prediction result and the equipment off-network prediction result to a monitoring center.
In an embodiment, after the step S20 of classifying the operation information of the micro base station, before the step S30 of inputting the alarm information, the control information and the monitoring information into the pre-constructed automatic alarm recognition model and the device off-grid prediction model, the method further includes: and storing the alarm information, the control information and the monitoring information in a data caching module.
In this embodiment, the data cache module is configured to receive the classified alarm information, control information, and monitoring information, and forward the classified alarm information, control information, and monitoring information to the automatic alarm identification model and the device off-network prediction model in real time.
In one embodiment, the step S30 of inputting the alarm information into the pre-constructed automatic alarm recognition model to obtain the fault alarm prediction result includes:
acquiring a training sample set of alarm information; in this embodiment, the alarm information in the training sample set is historical alarm information, and the historical alarm information needs to include the following fields: time, area, equipment number, alarm information, fault category.
And constructing a machine learning model, inputting a training sample set of the alarm information into the machine learning model for training to obtain a pre-constructed automatic alarm identification model.
In the embodiment, the alarm information in the training sample set is input into a machine learning model, the alarm information in the training sample set is cleaned, subjected to duplication removal and noise reduction, and then subjected to alarm data processing by using a TF or TF-IDF algorithm; the TF-IDF is a text word segmentation technology for data mining, the TF (term frequency) is word frequency, and the IDF (inverse Document frequency) is inverse text frequency, so that the weight of corpus data with excessive occurrence frequency can be effectively reduced. The TF-IDF algorithm is used for processing the alarm information, so that the importance degree of the linguistic data in the alarm information can be well measured. Of course, if the used alarm information is relatively uniform and there is no frequent alarm information of the base station in the hot section, it may be considered that only TF is used for processing the alarm information.
Inputting a training sample set of alarm information into the machine learning model for training, wherein the training sample set of alarm information comprises:
and inputting the training sample set of the alarm information into a machine learning model, and training the machine learning model by adopting a LightGBM or XGboost algorithm.
In the embodiment, the LightGBM algorithm alone is more predictive and faster than the XGBoost algorithm alone, and can be used as the main algorithm. However, for better results, it is also considered to fuse multiple algorithms to obtain better results, and a weighted fusion method is used here, and other main algorithms involved are XGBoost/extreme gradient boost integration tree, GBDT/gradient boost tree, Random _ forest (rf)/Random forest, SVM/support vector machine. In the embodiment, the XGboost/GBDT/RF/SVM algorithm model is used for simultaneously predicting the information to be predicted, and then the classification values score of the single learners are given according to experienceiDetermining the appropriate weight wiThen multiplied by weights respectively and then summediwiscoreiAnd obtaining the final fusion result. It should be noted that, in this embodiment, the LightGBM, XGBoost, RF single algorithm or fusion algorithm is used, and the prediction effect of specific data is determined.
And finally, deploying the trained automatic alarm recognition model to a server, inputting newly acquired alarm information into the trained automatic alarm recognition model by using the server to perform automatic alarm association and root cause recognition calculation, and uploading a finally generated model result (fault alarm prediction result) to a specified position of a monitoring center through the server to be stored, so that operation and maintenance personnel can check the model at any time. Meanwhile, based on manual experience, the fault causes can be matched with a fixed method to solve the faults, the system sets a solving strategy for each possible fault in a one-to-one correspondence mode, after the root causes are obtained through a model algorithm, the results are sent to an automatic recovery module, and after the module receives input, automatic operation is omitted according to a matching fault self-healing strategy which is set in advance, so that the faults can be solved automatically.
In this embodiment, a great amount of acquired alarm information of the micro base station is obtained, the alarm information is input into the automatic alarm recognition model, the alarm information in the training sample set is cleaned, processed, integrated and root cause judged, a fault result with the highest probability is obtained from the alarm information and is used as a fault alarm prediction result, the fault alarm prediction result is sent to the monitoring center, and a program is started to recover the fault.
In this embodiment, the operating environment of the automatic alarm recognition model in the server is python, and whether the MLlib library or the sklern library of pyspark is used to implement the algorithm may be determined according to a demand scenario.
In an embodiment, in step S30, inputting the control information and the monitoring information into a pre-constructed device off-grid prediction model to obtain a device off-grid prediction result, where the method includes:
acquiring a training sample set of control information and monitoring information; in this embodiment, the control information and the monitoring information in the training sample set are historical control information and monitoring information, where the control information includes basic equipment information and equipment configuration information, and the monitoring information includes a base station number, a base station operation log, an FSU number, an FSU operation log, an FSU mounted equipment operation log, offline time, and offline duration.
Then, cleaning, removing the weight and reducing the noise of the control information and the monitoring information in the training sample set, and integrating the time sequence characteristics of the control information and the monitoring information in the training sample set according to the time granularity to obtain the characteristic data of the control information and the monitoring information;
selecting proper characteristics from the characteristic data of the control information and the monitoring information as training characteristic data, and carrying out normalization processing and independent heat treatment on the training characteristic data;
and (3) constructing a deep neural network, inputting training characteristic data after normalization processing and independent heat processing into the deep neural network for training, and obtaining a pre-constructed equipment off-network prediction model.
And inputting the training characteristic data after the normalization processing and the one-way processing into the deep neural network, and training the deep neural network by adopting DNN and LSTM algorithms. In this embodiment, dnn (deep Neural networks) is a deep Neural network model, and LSTM is generally called a long-term and short-term memory network, and can well learn long-term laws. When in use, basic characteristic data is input into DNN, and time sequence characteristic data in a certain time range is input into LSTM, so that a good prediction effect is obtained.
And finally, deploying the equipment off-network prediction model to a server, and uploading the generated model prediction result to a specified position of the monitoring center platform through the server for storage.
Referring to fig. 2, fig. 2 is a block diagram of a micro base station monitoring apparatus according to an embodiment, where the monitoring apparatus includes a base station monitoring unit 10, a data classifying unit 20, a data predicting unit 30, and a result monitoring unit 40.
The base station monitoring unit 10 is used for acquiring operation information of the micro base station. The embodiment acquires the operation information of the micro base station through the monitoring unit FSU. Referring to fig. 3, the FSU is a minimum subsystem of the dynamic loop monitoring system, and is composed of a plurality of monitoring modules and other auxiliary devices, and may directly collect data of devices configured by the micro base station and process the data, and the FSU may include processing such as data sampling, data forwarding, aggregation, filtering, and data relaying. The FSU and the monitoring center are interconnected through the Internet, such as WebService and FTP modes, and the FSU and the monitoring center form a complete same socket protocol standard at the same time. The data stream interaction between the FSU and the monitoring center adopts an interface based on the Soap + XML + text file technology, which requires access to both parties: the monitoring center provides WebService service, and the FSU registers, reports alarm information, reports monitoring point data and reports configuration data of the dynamic ring equipment to the monitoring center; the method comprises the steps that an FSU provides WebService service, a monitoring center actively requests monitoring point data, writes a monitoring point set value, requests monitoring point threshold data, writes monitoring point threshold data, acquires FSU registration information, sets FSU registration information, acquires FTP information of the FSU, sets FTP information of the FSU, synchronizes time, acquires FSU state information (heartbeat mechanism), updates an FSU state information acquisition period, restarts the FSU, requests the configuration data of the dynamic ring equipment and writes the configuration data of the dynamic ring equipment; the FSU provides FTP service, and the monitoring center acquires configuration data (refrigeration and heating modes, temperature and humidity values, power values, voltage, current, electricity consumption and the like) of monitored objects (an air conditioner, a fuse wire, an electricity meter and the like) in batches, acquires monitoring image files, acquires activities, historical alarm synchronization files, acquires monitoring point performance data files, uploads FSU related files and acquires log files.
The data classifying unit 20 is configured to classify the operation information of the micro base station to obtain corresponding alarm information, control information, and monitoring information. The alarm information comprises alarm information generated on hardware and software of the micro base station equipment; the control information comprises signaling data, interactive data, configuration data of the micro base station, the monitoring unit FSU and the equipment mounted by the micro base station and the monitoring unit FSU; the monitoring information includes all available data on the base station device, such as operating parameters and states of the system, debugging and warning information of software, service data, and the like.
The data prediction unit 30 is configured to input alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; and inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result.
The result monitoring unit 40 is configured to send the failure alarm prediction result and the device off-network prediction result to the monitoring center.
In an embodiment, after classifying the operation information of the micro base station, before the step S30 inputs the alarm information, the control information, and the monitoring information into the pre-constructed automatic alarm identification model and the device off-network prediction model, the method further includes: and storing the alarm information, the control information and the monitoring information in a data caching module.
In one embodiment, inputting the alarm information into a pre-constructed automatic alarm recognition model to obtain a failure alarm prediction result, includes:
acquiring a training sample set of alarm information; in this embodiment, the alarm information in the training sample set is historical alarm information, and the historical alarm information needs to include the following fields: time, area, equipment number, alarm information, fault category.
And constructing a machine learning model, inputting a training sample set of the alarm information into the machine learning model for training to obtain a pre-constructed automatic alarm identification model.
Inputting a training sample set of alarm information into the machine learning model for training, wherein the training sample set of alarm information comprises:
and inputting the training sample set of the alarm information into a machine learning model, and training the machine learning model by adopting a LightGBM or XGboost algorithm.
In an embodiment, in step S30, inputting the control information and the monitoring information into a pre-constructed device off-grid prediction model to obtain a device off-grid prediction result, where the method includes:
acquiring a training sample set of control information and monitoring information; in this embodiment, the control information and the monitoring information in the training sample set are historical control information and monitoring information, where the control information includes basic equipment information and equipment configuration information, and the monitoring information includes a base station number, a base station operation log, an FSU number, an FSU operation log, an FSU mounted equipment operation log, offline time, and offline duration.
Then, cleaning, removing the weight and reducing the noise of the control information and the monitoring information in the training sample set, and integrating the time sequence characteristics of the control information and the monitoring information in the training sample set according to the time granularity to obtain the characteristic data of the control information and the monitoring information;
selecting proper characteristics from the characteristic data of the control information and the monitoring information as training characteristic data, and carrying out normalization processing and independent heat treatment on the training characteristic data;
and (3) constructing a deep neural network, inputting training characteristic data after normalization processing and independent heat processing into the deep neural network for training, and obtaining a pre-constructed equipment off-network prediction model.
And inputting the training characteristic data after the normalization processing and the one-way processing into the deep neural network, and training the deep neural network by adopting DNN and LSTM algorithms. In this embodiment, dnn (deep Neural networks) is a deep Neural network model, and LSTM is generally called a long-term and short-term memory network, and can well learn long-term laws. When in use, basic characteristic data is input into DNN, and time sequence characteristic data in a certain time range is input into LSTM, so that a good prediction effect is obtained.
And finally, deploying the equipment off-network prediction model to a server, and uploading the generated model prediction result to a specified position of the monitoring center platform through the server for storage.
In the embodiment of the invention, due to the existence of the micro base station monitoring device provided by the embodiment of the invention, the micro base station does not only interact with the monitoring unit FSU and the monitoring center to acquire, store and forward data, and the micro base station is interconnected with the monitoring center through the monitoring device, so that the micro base station can indirectly forward, classify, analyze and calculate the data through the system, and the data processing and analysis are more flexible and convenient.
Those skilled in the art will appreciate that all or part of the functions of the various methods in the above embodiments may be implemented by hardware, or may be implemented by computer programs. When all or part of the functions of the above embodiments are implemented by a computer program, the program may be stored in a computer-readable storage medium, and the storage medium may include: a read only memory, a random access memory, a magnetic disk, an optical disk, a hard disk, etc., and the program is executed by a computer to realize the above functions. For example, the program may be stored in a memory of the device, and when the program in the memory is executed by the processor, all or part of the functions described above may be implemented. In addition, when all or part of the functions in the above embodiments are implemented by a computer program, the program may be stored in a storage medium such as a server, another computer, a magnetic disk, an optical disk, a flash disk, or a removable hard disk, and may be downloaded or copied to a memory of a local device, or may be version-updated in a system of the local device, and when the program in the memory is executed by a processor, all or part of the functions in the above embodiments may be implemented.
The present invention has been described in terms of specific examples, which are provided to aid understanding of the invention and are not intended to be limiting. For a person skilled in the art to which the invention pertains, several simple deductions, modifications or substitutions may be made according to the idea of the invention.
Claims (10)
1. A micro base station monitoring method is characterized by comprising the following steps:
acquiring operation information of the micro base station;
classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information;
inputting the alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result;
and sending the fault alarm prediction result and the equipment off-network prediction result to a monitoring center.
2. The micro base station monitoring method of claim 1, wherein after classifying the operation information of the micro base station, before inputting the alarm information, the control information, and the monitoring information into a pre-constructed automatic alarm recognition model and a device off-grid prediction model, further comprising:
and storing the alarm information, the control information and the monitoring information in a data caching module.
3. The micro base station monitoring method of claim 1, wherein inputting the alarm information into a pre-constructed automatic alarm recognition model to obtain a failure alarm prediction result, comprises:
acquiring a training sample set of alarm information;
and constructing a machine learning model, inputting the training sample set of the alarm information into the machine learning model for training to obtain a pre-constructed automatic alarm identification model.
4. The micro base station monitoring method of claim 1, wherein inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result comprises:
acquiring a training sample set of control information and monitoring information;
integrating time sequence characteristics of control information and monitoring information in a training sample set according to time granularity to obtain characteristic data of the control information and the monitoring information;
selecting proper characteristics from the characteristic data of the control information and the monitoring information as training characteristic data, and carrying out normalization processing and independent heat treatment on the training characteristic data;
and (3) constructing a deep neural network, inputting training characteristic data after normalization processing and independent heat processing into the deep neural network for training, and obtaining a pre-constructed equipment off-network prediction model.
5. The micro base station monitoring method of claim 3, wherein inputting the training sample set of the alarm information into the machine learning model for training comprises:
and inputting the training sample set of the alarm information into the machine learning model, and training the machine learning model by adopting a LightGBM or XGboost algorithm.
6. The micro base station monitoring method of claim 4, wherein inputting training feature data after normalization processing and unique heat processing into the deep neural network for training comprises:
inputting the training characteristic data after the normalization processing and the one-way processing into the deep neural network, and training the deep neural network by adopting DNN and LSTM algorithms.
7. A micro base station monitoring apparatus, comprising:
the base station monitoring unit is used for acquiring the operation information of the micro base station;
the data classification unit is used for classifying the operation information of the micro base station to obtain corresponding alarm information, control information and monitoring information;
the data prediction unit is used for inputting the alarm information into a pre-constructed automatic alarm identification model to obtain a fault alarm prediction result; inputting the control information and the monitoring information into a pre-constructed equipment off-grid prediction model to obtain an equipment off-grid prediction result;
and the result monitoring unit is used for sending the fault alarm prediction result and the equipment off-network prediction result to a monitoring center.
8. The micro base station monitoring apparatus of claim 7, wherein inputting the control information and the monitoring information into a pre-constructed device off-grid prediction model to obtain a device off-grid prediction result comprises:
acquiring a training sample set of control information and monitoring information;
integrating time sequence characteristics of control information and monitoring information in a training sample set according to time granularity to obtain characteristic data of the control information and the monitoring information;
selecting proper characteristics from the characteristic data of the control information and the monitoring information as training characteristic data, and carrying out normalization processing and independent heat treatment on the training characteristic data;
and (3) constructing a deep neural network, inputting training characteristic data after normalization processing and independent heat processing into the deep neural network for training, and obtaining a pre-constructed equipment off-network prediction model.
9. The micro base station monitoring apparatus of claim 7, wherein inputting the control information and the monitoring information into a pre-constructed device off-grid prediction model to obtain a device off-grid prediction result comprises:
acquiring a training sample set of control information and monitoring information;
integrating time sequence characteristics of control information and monitoring information in a training sample set according to time granularity to obtain characteristic data of the control information and the monitoring information;
selecting proper characteristics from the characteristic data of the control information and the monitoring information as training characteristic data, and carrying out normalization processing and independent heat treatment on the training characteristic data;
and (3) constructing a deep neural network, inputting training characteristic data after normalization processing and independent heat processing into the deep neural network for training, and obtaining a pre-constructed equipment off-network prediction model.
10. A computer-readable storage medium, characterized by comprising a program executable by a processor to implement the method of any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011100600.7A CN112367678A (en) | 2020-10-15 | 2020-10-15 | Micro base station monitoring method and device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011100600.7A CN112367678A (en) | 2020-10-15 | 2020-10-15 | Micro base station monitoring method and device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112367678A true CN112367678A (en) | 2021-02-12 |
Family
ID=74506770
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011100600.7A Pending CN112367678A (en) | 2020-10-15 | 2020-10-15 | Micro base station monitoring method and device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112367678A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113268370A (en) * | 2021-05-11 | 2021-08-17 | 西安交通大学 | Root cause alarm analysis method, system, equipment and storage medium |
CN113891377A (en) * | 2021-11-17 | 2022-01-04 | 西藏先锋绿能环保科技股份有限公司 | Automatic maintenance and tuning method for 5G small base station equipment |
CN117155761A (en) * | 2023-11-01 | 2023-12-01 | 睿至科技集团有限公司 | Alarm method and system based on intelligent dynamic ring monitoring management platform |
CN118075792A (en) * | 2024-04-19 | 2024-05-24 | 深圳市佳贤通信科技股份有限公司 | Base station alarm processing method based on TR069 protocol |
CN118075792B (en) * | 2024-04-19 | 2024-06-28 | 深圳市佳贤通信科技股份有限公司 | Base station alarm processing method based on TR069 protocol |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109905885A (en) * | 2018-04-12 | 2019-06-18 | 华为技术有限公司 | A kind of method and inspection device of determining inspection station list |
US20190379589A1 (en) * | 2018-06-12 | 2019-12-12 | Ciena Corporation | Pattern detection in time-series data |
CN110891283A (en) * | 2019-11-22 | 2020-03-17 | 超讯通信股份有限公司 | Small base station monitoring device and method based on edge calculation model |
CN111626506A (en) * | 2020-05-27 | 2020-09-04 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
-
2020
- 2020-10-15 CN CN202011100600.7A patent/CN112367678A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109905885A (en) * | 2018-04-12 | 2019-06-18 | 华为技术有限公司 | A kind of method and inspection device of determining inspection station list |
US20190379589A1 (en) * | 2018-06-12 | 2019-12-12 | Ciena Corporation | Pattern detection in time-series data |
CN110891283A (en) * | 2019-11-22 | 2020-03-17 | 超讯通信股份有限公司 | Small base station monitoring device and method based on edge calculation model |
CN111626506A (en) * | 2020-05-27 | 2020-09-04 | 华北电力大学 | Regional photovoltaic power probability prediction method based on federal learning and cooperative regulation and control system thereof |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113268370A (en) * | 2021-05-11 | 2021-08-17 | 西安交通大学 | Root cause alarm analysis method, system, equipment and storage medium |
CN113891377A (en) * | 2021-11-17 | 2022-01-04 | 西藏先锋绿能环保科技股份有限公司 | Automatic maintenance and tuning method for 5G small base station equipment |
CN117155761A (en) * | 2023-11-01 | 2023-12-01 | 睿至科技集团有限公司 | Alarm method and system based on intelligent dynamic ring monitoring management platform |
CN118075792A (en) * | 2024-04-19 | 2024-05-24 | 深圳市佳贤通信科技股份有限公司 | Base station alarm processing method based on TR069 protocol |
CN118075792B (en) * | 2024-04-19 | 2024-06-28 | 深圳市佳贤通信科技股份有限公司 | Base station alarm processing method based on TR069 protocol |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111210024B (en) | Model training method, device, computer equipment and storage medium | |
CN112367678A (en) | Micro base station monitoring method and device and storage medium | |
US11294754B2 (en) | System and method for contextual event sequence analysis | |
CN111177095A (en) | Log analysis method and device, computer equipment and storage medium | |
WO2019196869A1 (en) | Method for determining list of patrolling base stations, and patrolling apparatus | |
US11704189B1 (en) | System and method for autonomous data center operation and healing | |
US20210141779A1 (en) | System and method for facilitating an objective-oriented data structure and an objective via the data structure | |
US20210055719A1 (en) | System for predictive maintenance using generative adversarial networks for failure prediction | |
CN112379325A (en) | Fault diagnosis method and system for intelligent electric meter | |
CN112800428A (en) | Method and device for judging safety state of terminal equipment | |
WO2018228672A1 (en) | A method, an apparatus and a system for detecting alarm data | |
CN109359829A (en) | Electric power emergency event aid decision-making method and system based on history big data | |
CN112836843A (en) | Method and device for predicting base station out-of-service alarm | |
US20230188440A1 (en) | Automatic classification of correlated anomalies from a network through interpretable clustering | |
CN111724052B (en) | Intelligent evaluation system for ship turbine simulator | |
CN112801815B (en) | Power communication network fault early warning method based on federal learning | |
CN115146788A (en) | Training method and device of distributed machine learning model and electric equipment storage medium | |
US20230039273A1 (en) | Event prediction | |
CN115277473A (en) | Remote operation and maintenance method and device for edge gateway, computer equipment and storage medium | |
KR20220156266A (en) | Monitoring service apparatus and method for providing fault prediction of device based on transfer learning | |
CN115689320A (en) | Health management method and device for base station operation and computer readable storage medium | |
CN111626531A (en) | Risk control method, device, system and storage medium | |
Mohagheghi et al. | Fuzzy cognitive maps for identifying fault activation patterns in automation systems | |
Beshley et al. | AI-Based IoT System for Temperature Forecasting | |
CN115002871B (en) | Signal connection system, signal connection method, computer device, 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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210212 |