CN112836843B - Base station out-of-service alarm prediction method and device - Google Patents
Base station out-of-service alarm prediction method and device Download PDFInfo
- Publication number
- CN112836843B CN112836843B CN201911168434.1A CN201911168434A CN112836843B CN 112836843 B CN112836843 B CN 112836843B CN 201911168434 A CN201911168434 A CN 201911168434A CN 112836843 B CN112836843 B CN 112836843B
- Authority
- CN
- China
- Prior art keywords
- data
- base station
- weather information
- service
- alarm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012549 training Methods 0.000 claims abstract description 60
- 238000013528 artificial neural network Methods 0.000 claims abstract description 54
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 39
- 239000000284 extract Substances 0.000 claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims description 25
- 230000000306 recurrent effect Effects 0.000 claims description 14
- 230000015654 memory Effects 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 238000011056 performance test Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 16
- 239000011159 matrix material Substances 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 230000008034 disappearance Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000002360 preparation method Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 238000002759 z-score normalization Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005259 measurement Methods 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
- 230000008447 perception Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/04—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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the invention provides a method and a device for predicting a base station out-of-service alarm, wherein the method comprises the following steps: acquiring base station characteristic data and weather information data of an area where a base station is located; inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data. The apparatus performs the above method. The base station service exit warning prediction method and the base station service exit warning prediction device provided by the embodiment of the invention can be used for accurately and efficiently predicting the base station service exit warning in advance, so that the efficiency and the quality of network operation and maintenance are improved.
Description
Technical Field
The invention relates to the technical field of network operation and maintenance, in particular to a base station out-of-service alarm prediction method and device.
Background
The network operation and maintenance fault investigation is the main working content of the network operation and maintenance, wherein the most core work is to examine the base station service withdrawal alarm.
The current network operation and maintenance fault detection technical means mainly adopts a passive response scheme after the base station generates the service withdrawal alarm, and further relies on the manual experience of operation and maintenance personnel and an equipment manual to conduct root cause analysis and processing. Because the above technical means is that after the base station out-of-service alarm occurs and the base station stops serving, the user cannot normally access the network within a period of time after that. Therefore, the base station out-of-service alarm needs to be predicted in advance to realize prevention and improve the efficiency and quality of network operation and maintenance.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a method and a device for predicting a base station out-of-service alarm.
The embodiment of the invention provides a method for predicting a base station out-of-service alarm, which comprises the following steps:
acquiring base station characteristic data and weather information data of an area where a base station is located;
inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
Wherein the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted comprises:
training a cyclic neural network by adopting sample data of extracting site industrial parameter resource data and weather information data; the site industrial parameter resource data are parameter configuration state data capable of representing intrinsic properties of the base station and cell identification data.
Wherein the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted comprises:
training a cyclic neural network by adopting sample data for extracting network management performance statistical data and weather information data; the network management performance statistical data is key performance index data of the base station for wireless communication service.
Wherein the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted comprises:
training a cyclic neural network by adopting sample data of extracting dynamic environment monitoring data and weather information data; the power environment monitoring data are power monitoring data and environment monitoring data in the base station machine room.
Wherein the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted comprises:
training a cyclic neural network by adopting sample data for extracting historical alarm data and weather information data; the historical alarm data are the types and the frequencies of the service withdrawal alarms generated by the base station in a preset historical period.
The key performance index data is at least one of a wireless connection rate, a wireless disconnection rate, a connection time delay and a block error rate.
Wherein the recurrent neural network is LSTM.
The embodiment of the invention provides a base station out-of-service alarm prediction device, which comprises:
the acquisition unit is used for acquiring the characteristic data of the base station and the weather information data of the area where the base station is located;
the prediction unit is used for inputting the base station characteristic data and the weather information data into a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
An embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein,
the processor, when executing the computer program, performs the following method steps:
acquiring base station characteristic data and weather information data of an area where a base station is located;
inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
Embodiments of the present invention provide a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method steps of:
acquiring base station characteristic data and weather information data of an area where a base station is located;
inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
According to the base station service withdrawal alarm prediction method and device, the base station characteristic data and the weather information data of the area where the base station is located are input into the preset base station service withdrawal alarm prediction model, and the output result of the model is used as the base station service withdrawal alarm prediction result, so that the base station service withdrawal alarm prediction can be accurately and efficiently performed in advance, and the efficiency and quality of network operation and maintenance are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of an embodiment of a method for predicting a base station out-of-service alarm according to the present invention;
FIG. 2 is a flowchart of another embodiment of a method for predicting a base station out-of-service alarm according to the present invention;
FIG. 3 is a schematic diagram of a training set single sample according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of the basic unit of an LSTM according to an embodiment of the invention;
FIG. 5 is a schematic structural diagram of an embodiment of a base station apparatus for predicting a service withdrawal alarm according to the present invention;
fig. 6 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Fig. 1 is a flowchart of an embodiment of a base station service exit warning prediction method according to the present invention, as shown in fig. 1, and the base station service exit warning prediction method provided by the embodiment of the present invention includes the following steps:
s101: and acquiring the characteristic data of the base station and the weather information data of the area where the base station is located.
Specifically, base station characteristic data and weather information data of an area where the base station is located are obtained. The method steps may be performed by a computer device, and may specifically be a network management platform. Because the preset base station out-of-service alarm prediction model of the embodiment of the invention is based on the cyclic neural network, the cyclic neural network has the capability of data reduction and feature learning in the training process, the feature data corresponding to all reasons causing the out-of-service of the base station or abnormal feature data generated before the out-of-service occurs should be considered as much as possible in the feature extraction stage. The method specifically comprises the following steps: site industrial parameter resource data, network management performance statistical data, power environment monitoring data, historical alarm data and weather information data. The specific descriptions are as follows:
1) Site project resource data
The data is parameter configuration state data capable of representing the intrinsic attribute of the base station and cell identification data. For example: on time, geographical location, manufacturer, frequency number, physical cell identity (Physical Cell Identifier, abbreviated as "PCI"), coverage scenario, antenna hang-up, downward tilt angle of direction angle, etc. These data characterize the intrinsic properties of the base station, such as its geographic location, the coverage scenario, and the likelihood that the base station will be subjected to extreme weather effects.
2) Network management performance statistics
The data is key performance index data of the base station for wireless communication service, and can comprise 15-minute granularity wireless network key performance index (Key Performance Indicator, KPI) and performance test (Performance Measurement, PM) data extracted from a network management platform. Before a major failure occurs, the base station performance may fluctuate or degrade due to effects such as equipment aging damage, bad weather, etc. By capturing these changes in performance data, one can estimate the occurrence of a fault. The key performance indicator data may further include: performance indexes such as wireless connection rate, wireless disconnection rate, connection delay, block error rate and the like.
3) Dynamic environment monitoring data
The data are power monitoring data and environment monitoring data in a base station machine room. Part of the base station failure is due to base station outage and battery exhaustion, or due to extreme weather causing equipment failure. The power monitoring is to monitor the power supply voltage, current and the residual capacity of the storage battery in real time, and directly relates to whether the base station has a power failure risk or not; the environment monitoring detects the temperature, humidity and other information in the machine room, and has a leading prediction function for predicting the short circuit burnout of the plate circuit.
4) Historical alert data
The data is the type and frequency of the base station generating the out-of-service alarm in the preset history period, and the specific value of the preset history period can be set independently according to the actual situation. And counting the types and the frequencies of other secondary alarms which are accompanied when the out-of-service alarms which cause the faults occur. Based on the standard alert dictionary table, the categories of the statistical alert may include: the system has no License running alarm, the control surface of the base station S1 transmits an interrupt alarm, the monitoring equipment maintains abnormal link alarms and the like.
5) Weather information data
This type of data describes future weather conditions in the area where the base station is located. The temperature, humidity, weather probability of rain and snow, and some extreme weather early warning information (such as typhoons, slush and high temperature) of the city/county where the crawler crawls the base station can be used for assisting in fault prediction.
S102: inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
Specifically, inputting the base station characteristic data and the weather information data to a preset base station out-of-service warning prediction model, and taking an output result of the preset base station out-of-service warning prediction model as a base station out-of-service warning prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data. Modeling data with deep neural networks can use a variety of models, such as deep boltzmann network DBN, convolutional neural network CNN, recurrent neural network RNN, and so on.
The embodiment of the invention provides a prediction method aiming at the occurrence probability of the base station out-of-service alarm prediction. The prediction method is based on multidimensional base station characteristic data (and combination of the several types of data) in a period of time of a base station as input of a model, is used for predicting the probability of occurrence of a service withdrawal alarm of the base station in a period of time in the future, and is a prediction method based on a time sequence.
The cyclic neural network RNN has memory, is very suitable for predicting time series related data, is commonly used in the data prediction fields such as air temperature prediction, stock prediction and the like, and meets the requirements of the invention. Meanwhile, the naive RNN algorithm has a problem of gradient disappearance when the model is oversized due to its long-term dependence. The long-term and short-term memory network LSTM realizes the long-range association of information by introducing a leakage unit and a gating circulation unit, and avoids gradient disappearance.
Further, the embodiment of the invention can select a variant of the cyclic neural network RNN, namely the long-short-term memory network LSTM, for realizing the prediction of the base station take-off alarm.
Fig. 2 is a flowchart of a base station out-of-service alarm prediction method according to another embodiment of the present invention, as shown in fig. 2, including a model preparation phase, a model training phase, and a model prediction phase. The three phases are specifically described as follows:
step 1) model preparation stage
The method comprises the steps of generating preparation data for a preset base station out-of-service alarm prediction model, and constructing a training sample set. The training sample set takes a base station as a basic unit and consists of historical data of a plurality of base stations. Fig. 3 is a schematic diagram of a single sample of a training set according to an embodiment of the present invention, as shown in fig. 3, where data of a base station for a continuous period of time (assuming that input data includes a feature of T time, output data needs to include data of t+1 time, and it is guaranteed that an object to be predicted is at a future time of the input feature) forms a sample. Each sample includes both the characteristic data for the input and the actual value that is desired to be output, i.e., the training target. The input data comprise site engineering parameter resource data, network management performance statistical data, power environment monitoring data, alarm data and weather information data of the base station, and the training target data is whether the base station generates a service withdrawal alarm within a period of time (T to T+1) in the future, wherein the occurrence is 1, and the occurrence is not 0. And (3) inputting characteristic data into the model to obtain the probability of occurrence of the service withdrawal alarm in a future period of time, wherein the interval of the probability value is [0,1].
By associating the input feature data with the output target data, a training pattern is formed, such as that shown in fig. 3. Matrix X is the input matrix and matrix Y is the target matrix.
The X matrix comprises n columns which are respectively n-dimensional features constructed through various data sources; t+1 rows are respectively from time sequence 1 to time sequence T+1, where T+1 rows of data may be empty, f s,l The value of the first characteristic at the time s is obtained.
The Y matrix comprises m columns which are respectively target types to be predicted (mainly refer to the possible type of the out-of-service alarm in the embodiment of the invention); t+1 rows, which are time sequences 1 to T+1 respectively, since the present embodiment of the present invention aims to predict future time targets based on current information, the Y matrix needs to hold 2 to T+1 rows of data, i.e. delay 1 time unit, K, from the X matrix s,l And if the first out-of-service alarm occurs at the s moment, the occurrence is 1, and the occurrence is not 0.
Two operations are required after the training set is ready. The first step is normalization, and the Z-Score normalization method is utilized to normalize the data by columns so as to ensure the stability of data set distribution:
X :,j ＝(f :,j -f j,mean )/f j,std
y :,j ＝(k :,j -k j,mean )/k j,std
wherein f :,j To normalize all elements of the previous j-th column, x :,j For all elements of the j-th column after normalization, f j,mean Mean value of all element values in j-th column of whole sample set, f j,std Standard deviation for all elements of column j for the entire sample set. The whole sample set was normalized to a standard normal distribution with a mean of 0 and a variance of 1 by Z-Score normalization. Similar operations are also performed on the Y matrix to normalize the entire sample set.
The second step is the repair of the defect data. For the cells without data, the standard normal distribution is utilized to randomly generate numerical values for filling, and the statistical property of each column of data is not changed.
Step 2) model training stage
Training LSTM network weights by utilizing the data set constructed in the step 1) so as to realize the mapping from the relevant characteristic indexes of the cell fault alarm to the output of the outage alarm probability. The LSTM model is formed by cascading a plurality of LSTM units, is a prediction model based on time steps, and can input corresponding features at each time step. Based on the data set established by the service logic, the symptoms of failure occurrence such as the withdrawal alarm are hidden, and the characteristic information of each time step has different degrees of influence on the probability of the occurrence of the withdrawal alarm, and the influence degree is complex and cannot be determined manually. The LSTM algorithm can automatically learn the implicit influence degree information in the data by changing the weight transmitted by the unit, so as to realize modeling of the data. FIG. 4 is a schematic diagram of basic units of the LSTM according to the embodiment of the invention, as shown in FIG. 4:
the LSTM network is formed by a number of identical base units connected end to end, one time step for each unit. Wherein X is t Feature vector input for t time step, h t For output of t time steps, C t Is the state of the t time step. f (f) t ,i t ,o t Respectively correspond to a forgetting door, an input door and an output door. Sigma (·) is a Sigmoid activation function.
Training of the model is divided into two phases, forward propagation and reverse training. And in the forward propagation stage, feature vectors are input according to the time step sequence, and the unit state and the output of each unit step are calculated according to the following formula, wherein W corresponds to the network weight, and b corresponds to the network bias. First to forget the door f t And an input gate i t And (5) performing calculation. The forget gate determines the influence of the last time step state on the next time step state; the input gate determines the effect of the current time step input on the current state. The values of the two are 0-1, the 0 mark is completely abandoned, and 1 is completely reserved. The formula is as follows:
f t ＝σ(W f ·[h t-1 ,x t ]+b f )
i t ＝σ(W i ·[h t-1 ,x t ]+b i )
second, for the content of the input gate input, an alternative input vector needs to be constructedAnd utilize->f t 、i t 、C t-1 To construct the current time step state C t The formula is as follows:
then, each unit step calculates an output gate output. Output door o t And determining the reserved quantity of the state output information of the current time step, wherein the value is 0-1, the mark of 0 is completely abandoned, and 1 represents complete reservation. The calculation formula is as follows:
O t ＝σ(W o ·[h t-1 ,x t ]+b o )
h t ＝o t *tanh(C t )
finally, calculating an output predicted value of the current time sequence T, namely estimating the occurrence probability of the out-of-service alarm at the moment T+1 in the embodiment of the invention, wherein the calculation formula is as follows:
in the forward propagation process, mapping the base station characteristics based on time steps into alarm occurrence probability through an LSTM network; and in the reverse training process, the weights W, b and the like of the network are changed through training, so that the network prediction probability is more similar to the real probability. The training process is implemented by a time-based back propagation algorithm (BPTT).
The purpose of the BPTT algorithm is to minimize the loss function of the model. The loss function uses a cross entropy function to represent the difference between the predicted and actual values as follows:
the gradient of the loss function relative to each weight parameter can be calculated by using the deflector chain algorithm, and the following is taken as an example for Wf:
the gradients may be similarly solved for other weights, bias parameters Wi, wo, bf, bi, bo, V, c, etc. And training and updating all the weight and bias parameters by using a random gradient descent method.
Step 3) model prediction stage
After repeated iterative training, the model converges, and can be used for predicting the out-of-service alarm which leads to the failure of the base station. During prediction, performance data, historical alarm data, industrial parameter data and dynamic ring data of a current base station in the past for a period of time (less than T) and local weather data are input, input features of each time step are formed according to a time sequence, and a model is input, so that a fault probability prediction value at the moment T+1 can be obtained.
The embodiment of the invention obtains the service requirement for predicting the service withdrawal alarm probability based on the deep research on the operation and maintenance fault investigation of the wireless network. According to the characteristics of the requirement, a deep learning algorithm LSTM based on time sequence prediction is selected as a service modeling algorithm, and a back-service alarm probability prediction model is constructed. The embodiment of the invention considers the internal and external factors which cause the wireless base station to generate the service withdrawal alarm as far as possible, characterizes all details involved in the scenes such as performance degradation conditions of service withdrawal, and the like, and realizes the accurate mapping from the input characteristic data to the output probability through the training of the model weight. Compared with the traditional method for estimating regional service withdrawal alarm by experience, the embodiment of the invention realizes the refined service withdrawal probability prediction at the cell level. The method has guiding significance for the release of the operation and maintenance resources of the wireless base station and the selection of the patrol base station. Meanwhile, by preventing the accident, and utilizing a prediction mechanism, the occurrence frequency of actual service withdrawal can be reduced by overhauling in advance before the accident occurs, so that the customer perception is smoother.
According to the base station service withdrawal alarm prediction method provided by the embodiment of the invention, the base station characteristic data and the weather information data of the area where the base station is located are input into the preset base station service withdrawal alarm prediction model, and the output result of the model is used as the base station service withdrawal alarm prediction result, so that the base station service withdrawal alarm prediction can be accurately and efficiently performed in advance, and the efficiency and the quality of network operation and maintenance are further improved.
On the basis of the above embodiment, the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted includes:
specifically, training a cyclic neural network by adopting sample data of extracting site industrial parameter resource data and weather information data; the site industrial parameter resource data are parameter configuration state data capable of representing intrinsic properties of the base station and cell identification data. Reference is made to the above description and will not be repeated.
According to the base station out-of-service alarm prediction method provided by the embodiment of the invention, the cyclic neural network is trained by adopting the sample data extracted from the site industrial parameter resource data and the weather information data, so that the base station out-of-service alarm prediction can be further performed in advance, accurately and efficiently, and the efficiency and quality of network operation and maintenance are further improved.
On the basis of the above embodiment, the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted includes:
specifically, a cyclic neural network is trained by adopting sample data of extracted network management performance statistical data and weather information data; the network management performance statistical data is key performance index data of the base station for wireless communication service. Reference is made to the above description and will not be repeated.
According to the base station service withdrawal alarm prediction method provided by the embodiment of the invention, the cyclic neural network is trained by adopting the sample data for extracting the network management performance statistical data and the weather information data, so that the base station service withdrawal alarm prediction can be further performed in advance, accurately and efficiently, and the efficiency and quality of network operation and maintenance are further improved.
On the basis of the above embodiment, the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted includes:
specifically, training a cyclic neural network by adopting sample data of extracting dynamic environment monitoring data and weather information data; the power environment monitoring data are power monitoring data and environment monitoring data in the base station machine room. Reference is made to the above description and will not be repeated.
According to the base station service withdrawal alarm prediction method provided by the embodiment of the invention, the cyclic neural network is trained by adopting the sample data for extracting the dynamic environment monitoring data and the weather information data, so that the base station service withdrawal alarm prediction can be further performed in advance, accurately and efficiently, and the efficiency and quality of network operation and maintenance are further improved.
On the basis of the above embodiment, the training the recurrent neural network using the sample data from which the base station characteristic data and the weather information data are extracted includes:
specifically, training a cyclic neural network by adopting sample data for extracting historical alarm data and weather information data; the historical alarm data are the types and the frequencies of the service withdrawal alarms generated by the base station in a preset historical period. Reference is made to the above description and will not be repeated.
According to the base station service withdrawal alarm prediction method provided by the embodiment of the invention, the cyclic neural network is trained by adopting the sample data for extracting the historical alarm data and the weather information data, so that the base station service withdrawal alarm prediction can be further performed in advance, accurately and efficiently, and the efficiency and quality of network operation and maintenance are further improved.
On the basis of the foregoing embodiment, specifically, the key performance indicator data is at least one of a wireless connection rate, a wireless disconnection rate, a connection delay, and a block error rate. Reference is made to the above description and will not be repeated.
According to the base station service withdrawal alarm prediction method provided by the embodiment of the invention, the key performance index data is determined to be at least one of the wireless connection rate, the wireless disconnection rate, the connection delay and the block error rate, so that the key performance index can be comprehensively obtained, the characteristics affecting the base station service withdrawal alarm are further comprehensively considered, and the base station service withdrawal alarm prediction is optimized.
On the basis of the above embodiment, specifically, the recurrent neural network is LSTM. Reference is made to the above description and will not be repeated.
The base station out-of-service alarm prediction method provided by the embodiment of the invention can avoid gradient disappearance and optimize the training process of the model.
Fig. 5 is a schematic structural diagram of an embodiment of a base station service exit warning prediction device according to the present invention, and as shown in fig. 5, an embodiment of the present invention provides a base station service exit warning prediction device, which includes an obtaining unit 501 and a prediction unit 502, where:
the acquiring unit 501 is configured to acquire base station feature data and weather information data of an area where the base station is located; the prediction unit 502 is configured to input the base station feature data and the weather information data to a preset base station service withdrawal alarm prediction model, and take an output result of the preset base station service withdrawal alarm prediction model as a base station service withdrawal alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
Specifically, the acquiring unit 501 is configured to acquire base station feature data and weather information data of an area where the base station is located; the prediction unit 502 is configured to input the base station feature data and the weather information data to a preset base station service withdrawal alarm prediction model, and take an output result of the preset base station service withdrawal alarm prediction model as a base station service withdrawal alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
According to the base station service withdrawal alarm prediction device provided by the embodiment of the invention, the base station service withdrawal alarm prediction can be accurately and efficiently performed in advance by inputting the base station characteristic data and the weather information data of the area where the base station is located into the preset base station service withdrawal alarm prediction model and taking the output result of the model as the base station service withdrawal alarm prediction result, so that the efficiency and the quality of network operation and maintenance are improved.
The base station out-of-service alarm prediction device provided by the embodiment of the invention can be specifically used for executing the processing flow of each method embodiment, and the functions of the base station out-of-service alarm prediction device are not repeated herein, and can be referred to in the detailed description of the method embodiments.
Fig. 6 is a schematic diagram of an entity structure of an electronic device according to an embodiment of the present invention, as shown in fig. 6, where the electronic device includes: a processor (processor) 601, a memory (memory) 602, and a bus 603;
wherein, the processor 601 and the memory 602 complete communication with each other through the bus 603;
the processor 601 is configured to invoke program instructions in the memory 602 to perform the methods provided in the above method embodiments, for example, including: acquiring base station characteristic data and weather information data of an area where a base station is located; inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
The present embodiment discloses a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the methods provided by the above-described method embodiments, for example comprising: acquiring base station characteristic data and weather information data of an area where a base station is located; inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
The present embodiment provides a non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the methods provided by the above-described method embodiments, for example, including: acquiring base station characteristic data and weather information data of an area where a base station is located; inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by training a cyclic neural network through sample data which extracts the base station characteristic data and the weather information data.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (4)
1. The base station out-of-service alarm prediction method is characterized by comprising the following steps of:
acquiring base station characteristic data and weather information data of an area where a base station is located;
inputting the base station characteristic data and the weather information data to a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by adopting a sample data training cyclic neural network for extracting the base station characteristic data and the weather information data;
the training a recurrent neural network using sample data that extracts the base station characteristic data and the weather information data, comprising:
training a cyclic neural network by adopting sample data for extracting network management performance statistical data and weather information data; the network management performance statistical data is key performance index data of wireless communication service of the base station, and comprises wireless gateway key performance index and performance test data;
training a cyclic neural network by adopting sample data of extracting site industrial parameter resource data and weather information data; the site industrial parameter resource data are parameter configuration state data capable of representing intrinsic properties of the base station and cell identification data;
training a cyclic neural network by adopting sample data of extracting dynamic environment monitoring data and weather information data; the power environment monitoring data are power monitoring data and environment monitoring data in a base station machine room;
training a cyclic neural network by adopting sample data for extracting historical alarm data and weather information data; the history alarm data is the type and frequency of the service withdrawal alarm generated by the base station in a preset history period;
the key performance index data is at least one of a wireless connection rate, a wireless disconnection rate, a connection time delay and a block error rate;
the recurrent neural network is LSTM.
2. A base station take-off alarm prediction device, comprising:
the acquisition unit is used for acquiring the characteristic data of the base station and the weather information data of the area where the base station is located;
the prediction unit is used for inputting the base station characteristic data and the weather information data into a preset base station out-of-service alarm prediction model, and taking the output result of the preset base station out-of-service alarm prediction model as a base station out-of-service alarm prediction result; the preset base station take-off alarm prediction model is obtained by adopting a sample data training cyclic neural network for extracting the base station characteristic data and the weather information data;
the prediction unit includes:
the cyclic neural network training unit is used for training the cyclic neural network by adopting sample data for extracting the network management performance statistical data and the weather information data; the network management performance statistical data is key performance index data of wireless communication service of the base station, and comprises wireless gateway key performance index and performance test data;
training a cyclic neural network by adopting sample data of extracting site industrial parameter resource data and weather information data; the site industrial parameter resource data are parameter configuration state data capable of representing intrinsic properties of the base station and cell identification data;
training a cyclic neural network by adopting sample data of extracting dynamic environment monitoring data and weather information data; the power environment monitoring data are power monitoring data and environment monitoring data in a base station machine room;
training a cyclic neural network by adopting sample data for extracting historical alarm data and weather information data; the history alarm data is the type and frequency of the service withdrawal alarm generated by the base station in a preset history period;
the key performance index data is at least one of a wireless connection rate, a wireless disconnection rate, a connection time delay and a block error rate;
the recurrent neural network is LSTM.
3. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method of claim 1 when executing the computer program.
4. A non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the method according to claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911168434.1A CN112836843B (en) | 2019-11-25 | 2019-11-25 | Base station out-of-service alarm prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911168434.1A CN112836843B (en) | 2019-11-25 | 2019-11-25 | Base station out-of-service alarm prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112836843A CN112836843A (en) | 2021-05-25 |
| CN112836843B true CN112836843B (en) | 2024-04-09 |
Family
ID=75922332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911168434.1A Active CN112836843B (en) | 2019-11-25 | 2019-11-25 | Base station out-of-service alarm prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112836843B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113365297B (en) * | 2021-08-10 | 2021-11-12 | 广东南方电信规划咨询设计院有限公司 | Base station antenna performance monitoring method and device, electronic equipment and storage medium |
| CN114375035A (en) * | 2021-12-29 | 2022-04-19 | 中国电信股份有限公司 | Base station parameter adjusting method and device, electronic equipment and readable storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030046905A (en) * | 2001-12-07 | 2003-06-18 | 에스케이 텔레콤주식회사 | Method for Call Fail Cause Analysis in Mobile Communication System |
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN101742541A (en) * | 2008-11-13 | 2010-06-16 | 中国移动通信集团河北有限公司 | Early warning method and system of base station service quit |
| CN104270779A (en) * | 2014-10-17 | 2015-01-07 | 浪潮通信信息系统有限公司 | Wireless network fault cause preprocessing method and wireless network fault work order dispatching system |
| CN107295553A (en) * | 2017-08-21 | 2017-10-24 | 中国铁塔股份有限公司 | A kind of base station maintenance method and device |
| CN108063676A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信集团山西有限公司 | Communication network failure method for early warning and device |
-
2019
- 2019-11-25 CN CN201911168434.1A patent/CN112836843B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030046905A (en) * | 2001-12-07 | 2003-06-18 | 에스케이 텔레콤주식회사 | Method for Call Fail Cause Analysis in Mobile Communication System |
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN101742541A (en) * | 2008-11-13 | 2010-06-16 | 中国移动通信集团河北有限公司 | Early warning method and system of base station service quit |
| CN104270779A (en) * | 2014-10-17 | 2015-01-07 | 浪潮通信信息系统有限公司 | Wireless network fault cause preprocessing method and wireless network fault work order dispatching system |
| CN108063676A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信集团山西有限公司 | Communication network failure method for early warning and device |
| CN107295553A (en) * | 2017-08-21 | 2017-10-24 | 中国铁塔股份有限公司 | A kind of base station maintenance method and device |
Non-Patent Citations (5)
| Title |
|---|
| Predicting malfunction of mobile network base station using machine learning approach;Yin-Hsin Liu, 等;《2019 20th Asia-Pacific Network Operations and Management Symposium》;第1-4页 * |
| 基于大数据的 5G 基站退服成本估算;魏鹏涛,等;《电子技术应用》;第45卷(第10期);第15-16页 * |
| 基于神经网络的通信网络告警关联分析及应用;刘洪波,等;《电信技术》(第5期);第32-35页 * |
| 基于集中监控数据资源的4G基站退服故障预警模型;王洋, 等;《电信科学》;第32卷(第7期);第188-196页 * |
| 数据挖掘在移动基站退服故障预测中的研究;石少民;《中国优秀硕士学位论文全文数据库信息科技辑》(第10期);第I136-82页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112836843A (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108513251B (en) | Positioning method and system based on MR data | |
| US7243049B1 (en) | Method for modeling system performance | |
| CN112836843B (en) | Base station out-of-service alarm prediction method and device | |
| CN105260823A (en) | Method and system for evaluating health status of major equipment | |
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN105182122A (en) | Fault early warning method of random power supply access equipment | |
| CN113887846A (en) | Out-of-tolerance risk early warning method for capacitive voltage transformer | |
| CN113868953B (en) | Multi-unit operation optimization method, device and system in industrial system and storage medium | |
| CN114168444A (en) | Dynamic operation and maintenance repair reporting model based on monitoring big data | |
| CN105471647A (en) | Power communication network fault positioning method | |
| CN112379325A (en) | Fault diagnosis method and system for intelligent electric meter | |
| CN112884199A (en) | Method and device for predicting faults of hydropower station equipment, computer equipment and storage medium | |
| CN113191074A (en) | Machine room power supply parameter detection method for data center | |
| CN115409283A (en) | Equipment failure prediction method, equipment failure prediction device, equipment and storage medium | |
| CN103942251A (en) | Method and system for inputting high altitude meteorological data into database based on multiple quality control methods | |
| CN115033450A (en) | Bayesian cluster monitoring early warning analysis method based on distribution | |
| CN116794510A (en) | Fault prediction method, device, computer equipment and storage medium | |
| CN117557415A (en) | Community resource management method and system based on intelligent property | |
| CN108446202A (en) | A kind of judgment method of the safe condition of calculator room equipment | |
| CN117216713A (en) | Fault delimiting method, device, electronic equipment and storage medium | |
| CN108664696B (en) | Method and device for evaluating running state of water chiller | |
| CN116714469A (en) | Charging pile health monitoring method, device, terminal and storage medium | |
| CN109739210B (en) | Method and device for evaluating health state of equipment component | |
| CN111612129A (en) | Method and device for predicting state of isolating switch and storage medium | |
| CN115913699B (en) | Power distribution network lateral access detection method, device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |