CN112203311B - Network element abnormity diagnosis method, device, equipment and computer storage medium - Google Patents
Network element abnormity diagnosis method, device, equipment and computer storage medium Download PDFInfo
- Publication number
- CN112203311B CN112203311B CN201910609173.6A CN201910609173A CN112203311B CN 112203311 B CN112203311 B CN 112203311B CN 201910609173 A CN201910609173 A CN 201910609173A CN 112203311 B CN112203311 B CN 112203311B
- Authority
- CN
- China
- Prior art keywords
- network element
- data
- target network
- kpi data
- layer
- 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 47
- 238000003745 diagnosis Methods 0.000 title claims abstract description 45
- 230000000875 corresponding effect Effects 0.000 claims abstract description 51
- 238000012360 testing method Methods 0.000 claims abstract description 41
- 238000004891 communication Methods 0.000 claims abstract description 18
- 230000002596 correlated effect Effects 0.000 claims abstract description 15
- 238000012549 training Methods 0.000 claims description 91
- 238000013528 artificial neural network Methods 0.000 claims description 35
- 230000005856 abnormality Effects 0.000 claims description 30
- 230000006870 function Effects 0.000 claims description 25
- 230000002159 abnormal effect Effects 0.000 claims description 19
- 238000012795 verification Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000005457 optimization Methods 0.000 claims description 8
- 238000012423 maintenance Methods 0.000 abstract description 8
- 210000002569 neuron Anatomy 0.000 description 19
- 238000010606 normalization Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 238000013459 approach Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/04—Arrangements for maintaining operational condition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/08—Testing, supervising or monitoring using real traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention relates to the technical field of communication, and discloses a method, a device, equipment and a computer storage medium for diagnosing network element abnormity, wherein the method comprises the following steps: acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to an NFVI layer and the target network element to obtain test data; inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period; and carrying out abnormity diagnosis on the target network element according to the predicted KPI data of the target network element and the real KPI data of the target network element. By the method, the network element abnormity is diagnosed according to the error between the real KPI data and the predicted KPI data of the network element, so that the abnormity of the network element can be diagnosed before the network element fails, and the network operation and maintenance efficiency is improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of communication, in particular to a network element abnormity diagnosis method, a device, equipment and a computer storage medium.
Background
With the progress of mobile communication technology, data services develop rapidly, the structure of a mobile communication network becomes more and more complex, and the number of network elements in the mobile communication network is also increasing, which puts higher demands on the maintenance work of the communication network.
One of the key tasks of the maintenance of the communication network is network element fault diagnosis, and in the process of implementing the embodiment of the present invention, the inventor finds that: the existing network element fault diagnosis method mainly sets a threshold value directly for a network element KPI, and the method can only diagnose the fault which occurs and can not detect the abnormity of the network element before the network element fault.
Disclosure of Invention
In view of the foregoing, embodiments of the present invention provide a method, an apparatus, a device, and a computer storage medium for network element abnormality diagnosis, which overcome the foregoing problems or at least partially solve the foregoing problems.
According to an aspect of an embodiment of the present invention, there is provided a network element abnormality diagnosis method, including:
acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to an NFVI layer and the target network element to obtain test data; inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period, wherein the prediction model is obtained by training according to a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a VNF layer target network element, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to a NFVI layer and the target network element; and carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
In an optional manner, performing an anomaly diagnosis on the target network element according to an error between the predicted KPI data of the target network element and the actual KPI data of the target network element includes: calculating the error between each KPI data in the predicted KPI data of the target network element and the corresponding KPI data in the real KPI data of the target network element; calculating the root mean square error of the error in the preset time period; and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold value, determining that the target network element is abnormal.
In an alternative mode, calculating the root mean square error of the error in the preset time period includes:
according to the formula
Calculating a root mean square error of the error over the preset time period, wherein,
and
respectively representing the ith predicted KPI data and the real KPI data at the moment that the predicted time is t + a, and m represents the number of minutes contained in the preset time period.
In an optional manner, after obtaining the test data, the method further comprises: carrying out normalization processing on the test data to obtain standard test data; inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period, wherein the method comprises the following steps: and inputting the standard test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period.
In an optional manner, before obtaining the test data, the method further comprises: constructing an LSTM neural network framework; normalizing the obtained multiple groups of training data to obtain standard training data; converting the dimensionality of each set of training data in the standard training data into three-dimensional training data; and training the LSTM neural network frame according to the three-dimensional training data to obtain the prediction model.
In an alternative approach, an LSTM neural network framework is constructed, comprising: an LSTM neural network framework is constructed that includes one output layer, sixteen hidden layers, and one output layer, where the sixteen hidden layers include eight LSTM layers and eight dropout layers.
In an alternative manner, training the LSTM neural network framework according to multiple sets of training data to obtain the prediction model includes: obtaining the weight of the LSTM neural network framework according to the multiple groups of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a prediction model according to the weight with the minimum loss function value.
According to another aspect of the embodiments of the present invention, there is provided a network element abnormality diagnosis apparatus, including: the device comprises an acquisition module, an input module and an abnormality diagnosis module, wherein the acquisition module is used for acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to an NFVI layer and the target network element to obtain test data; an input module, configured to input the test data into a prediction model, so as to obtain predicted KPI data of the target network element within a preset time period, where the prediction model is obtained by training according to multiple sets of training data, and each set of the multiple sets of training data includes KPI data of a VNF layer target network element, KPI data of a VNF layer-associated network element associated with the target network element, and KPI data of a NFVI layer-associated target network element; and the abnormity diagnosis module is used for carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
In an optional manner, the abnormality diagnosis module is further configured to calculate an error between each KPI data in the predicted KPI data of the target network element and a corresponding KPI data in the actual KPI data of the target network element; calculating the root mean square error of the error in the preset time period; and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold value, determining that the target network element is abnormal.
In an alternative mode, calculating the root mean square error of the error in the preset time period includes: according to the formula
Calculating a root mean square error of the error over the preset time period, wherein,
and
respectively representing predicted timesAnd predicting KPI data and real KPI data for the ith item at the moment of t + a, wherein m represents the number of minutes contained in the preset time period.
In an optional manner, the apparatus further comprises: the construction module is used for constructing an LSTM neural network framework; the normalization module is used for normalizing the acquired multiple groups of training data to obtain standard training data; the conversion module is used for converting the dimensionality of each group of training data in the standard training data into three-dimensional training data; and the training module is used for training the LSTM neural network frame according to the three-dimensional training data to obtain the prediction model.
In an optional manner, the building module is further configured to build an LSTM neural network framework comprising one output layer, sixteen hidden layers and one output layer, wherein the sixteen hidden layers comprise eight LSTM layers and eight dropout layers.
In an optional manner, the training module is further configured to obtain weights of the LSTM neural network framework according to the plurality of sets of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a prediction model according to the weight with the minimum loss function value.
In an optional manner, the apparatus further comprises: and the verification module is used for verifying the prediction model according to the multiple groups of verification data. The training module is further used for retraining the prediction model when the accuracy of the multiple groups of verification data is lower than a preset threshold.
According to another aspect of the embodiments of the present invention, there is provided a network element abnormality diagnosis apparatus, including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation corresponding to the network element abnormity diagnosis method.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium, where at least one executable instruction is stored in the storage medium, and the executable instruction causes the processor to perform an operation corresponding to the above-mentioned network element abnormality diagnosis method.
According to the embodiment of the invention, the obtained test data is input into the prediction model to obtain the predicted KPI data of the target network element in the preset time period, and the target network element is subjected to abnormal diagnosis according to the error between the predicted KPI data and the actual KPI data in the preset time period, so that the abnormal diagnosis can be carried out on the network element before the network element fails, and the network operation and maintenance efficiency is improved.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and the embodiments of the present invention can be implemented according to the content of the description in order to make the technical means of the embodiments of the present invention more clearly understood, and the detailed description of the present invention is provided below in order to make the foregoing and other objects, features, and advantages of the embodiments of the present invention more clearly understandable.
Drawings
Various additional advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a flowchart illustrating a network element abnormality diagnosis method according to a first embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for diagnosing network element abnormality according to a second embodiment of the present invention;
fig. 3 shows a flowchart of a method for diagnosing network element abnormality according to a third embodiment of the present invention;
fig. 4 shows a functional block diagram of a network element abnormality diagnosis apparatus according to a fourth embodiment of the present invention;
fig. 5 shows a schematic structural diagram of a network element abnormality diagnosis device according to a fifth embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of a network element abnormality diagnosis method according to a first embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step 110: and acquiring KPI data of a VNF layer target network element, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element in a preset time window to obtain test data.
The VNF (virtual Network Function) is a virtual Network Function corresponding to a conventional telecommunication service Network, and a physical Network element in the conventional telecommunication service Network is mapped as a virtual Network element, so that the Function of the physical Network element can be realized by pure software. The virtual Network element operates on a Network Function Virtualization Infrastructure (NFVI), and the NFVI provides virtual resources for the virtual Network element, such as calculation, storage, network interworking, and the like. KPI (Key Performance Indication) data is Key Performance indicator data when a network element runs, and is used for representing the running state of the network element. The target network element is one of all network elements of the VNF layer. For the determined target network element of the VNF layer, KPI data corresponding to the target network element and associated network elements associated with the target network element by the VNF layer and the NFVI layer are determined.
The KPI data of the target network element and the KPI data of the associated network element both include attributes such as service load, service success rate, throughput, error code times, etc., and the KPI data corresponding to the NFVI layer and the target network element includes attributes such as CPU utilization rate, I/O rate, memory utilization rate, read-write response duration, etc., and in the specific implementation process, several of the attributes may be selected as the KPI data, the KPI attribute of the target network element and the KPI attribute category of the associated network element may be the same or different, and the number of the selected attribute categories may be the same or different. Taking into account that the KPI data of a network element has time variability, the KPI data in a certain time period in the recent past is obtained through a preset time window to predict the KPI data of a target network element in a certain time period in the future more accurately.
Step 120: and inputting the test data into the prediction model to obtain predicted KPI data of the target network element in a preset time period.
The prediction model is obtained by training according to a plurality of groups of training data, wherein each group of the plurality of groups of training data comprises KPI data of a VNF layer target network element, KPI data of a correlated network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element.
When a prediction model is trained using a plurality of sets of training data, the prediction model may be trained on a prediction model that can predict a certain KPI data, or may be trained on a prediction model that can predict all KPI data. When a prediction model capable of predicting a certain KPI data is trained, in order to effectively diagnose the abnormality of the network element, a prediction model needs to be trained for each KPI data to predict all KPI data.
In some embodiments, the predictive model is trained on the LSTM neural network framework based on multiple sets of training data. The LSTM neural network is a neural network with a memory function, the output of each LSTM neuron of a hidden layer is stored in a cache, the data stored in the cache is used as a part of the input when the LSTM neuron has data input next time, the output of the LSTM neuron is put into the cache at each time point, and the value in the cache is covered at the next time point. The LSTM neuron comprises three gates, a forgetting gate, an input gate and an output gate, wherein the forgetting gate determines information h stored at the last moment t-1 The formula of the calculation of the discarded and retained information is: f. of t ＝σ(W f ·[h t-1 ,x t ]+b f ) Wherein x is t Representing input information, b f For input layer offset vectors, σ denotes sigmoidFunction, W f The weight of the forgetting gate is represented, the output result of the forgetting gate is a number between 0 and 1, 1 represents "completely retaining the information", and 0 represents "completely discarding the information". Input gate determines last time neuron state C t-1 The calculation formula of the information needing to be updated is as follows: i.e. i t ＝σ(W i ·[h t-1 ,x t ]+b i )，
Wherein, C t Representing the state of the neuron at the current moment, W i 、W c Respectively representing the weight of the input gate, b i And b c Respectively, input layer bias vectors. The output contains two parts, one part is the total output, the other part is the output for inputting the next LSTM neuron, and the calculation formula of the total output is as follows: o t ＝σ(W o [h t-1 ,x t ]+b o ) The computational formula for inputting the output of the next LSTM neuron is: h is a total of t ＝o t *tanh(C t ) Wherein W is o As output layer weights, b o Is the output layer bias vector. At the time of obtaining the total output o t Then to o t And obtaining an output result by denormalization.
Before the testing step of step 110 is executed, an LSTM neural network framework is constructed, and normalization processing is carried out on multiple groups of acquired training data to obtain standard training data; converting the dimensionality of each set of training data in the standard training data into three-dimensional training data; and training the LSTM neural network framework according to the three-dimensional training data to obtain a prediction model. Normalization is the scaling of test data to fall within a specific interval to eliminate the magnitude difference between different types of data. In particular embodiments, the specific interval is generally [0,1], and in one particular embodiment, normalized according to the following equation:
X std ＝X sca ×(X max -X min )+X min
wherein, X std Is a set of standard training data, X is a set of training data, X max And X max Respectively, a maximum value and a minimum value for the set of training data.
Considering that the LSTM neural network requires a three-dimensional array for the shape of the input data, after obtaining the standard test data, the standard test data needs to be subjected to data transformation to convert the standard test data into three-dimensional training data. For example, the standard training data includes a data number of each piece of data and KPI data corresponding to the data, and when conversion is performed, a time feature is added to convert the standard test data into three-dimensional training data. It should be noted that the multiple sets of training data are obtained by dividing the acquired historical KPI data according to a preset time window, where the preset time window is consistent with the preset time window corresponding to the test data in step 110, and the added time characteristic is the time corresponding to the preset time window.
It should be understood that the processing of the test data is consistent with the processing of the training data and will not be described in detail herein.
In a specific embodiment, the structure of the constructed LSTM neural network is shown in fig. 2, and the LSTM neural network comprises one input layer, sixteen hidden layers and one output layer, wherein the sixteen hidden layers comprise eight LSTM layers and eight dropout layers. The input layer is used for inputting KPI data of a VNF layer target network element in a preset time window, KPI data of a correlated network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element. The number of neurons included in the input layer is related to the number of attributes of KPI data included in each set of training data, for example, if the number of KPI attributes of a target network element included in each set of training data is j, the number of KPI attributes of an associated network element associated with the target network element is k, and the number of KPI attributes of an NFVI layer corresponding to the target network element is l, then the number of neurons in the input layer should be set to j + k + l. The number of the neurons of the output layer is related to time corresponding to a preset time period, if the preset time period is m minutes, the number of the corresponding neurons of the output layer is m, each neuron is used for outputting KPI data corresponding to each minute, if the KPI data is a certain KPI data, the output result of each neuron is a determined numerical value, and if the KPI data is all KPI data corresponding to a certain minute, the output result of each neuron is an array. The eight LSTM layers and the eight dropout layers are in one-to-one correspondence, and each LSTM layer is connected with one dropout layer and used for discarding neurons according to a preset probability p, so that overfitting is avoided. In a specific embodiment, the first and second LSTM layers are configured with 128 neurons, the third and fourth LSTM layers are configured with 64 neurons, and the fifth and sixth LSTM layers are configured with 16 neurons.
During training, obtaining the weight of the LSTM neural network framework according to a plurality of groups of training data, and calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a prediction model according to the weight with the minimum loss function value. Where the loss function may be set manually by a person skilled in the art in practicing embodiments of the present invention, in a specific implementation, the loss function is chosen to be a Mean Squared Error (MSE) function. The optimization algorithm selects a gradient descent optimization algorithm for improving the learning speed of the traditional gradient descent.
After the training is completed to obtain a prediction model, verifying the prediction model according to a plurality of groups of verification data; and when the prediction accuracy of the multiple groups of verification data is lower than a preset threshold value, retraining the prediction model. The multiple groups of verification data and the multiple groups of training data are all from acquired historical KPI data, and in the specific implementation process, the multiple groups of training data can be proportionally divided into training data for training a prediction model and verification data for testing the model.
Step 130: and carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
In this step, if the error between the predicted KPI data of the target network element and the actual KPI data of the target network element reaches the condition of network element abnormality, it can be determined that the target network element is abnormal. In a specific implementation manner, the abnormal condition of the target network element is a preset threshold, and when an error between the predicted KPI data and the actual KPI data exceeds the preset threshold, it indicates that the KPI data has a sign of degradation, and the target network element is abnormal.
According to the embodiment of the invention, the obtained test data is input into the prediction model to obtain the predicted KPI data of the target network element in the preset time period, and the target network element is subjected to abnormal diagnosis according to the error between the predicted KPI data and the real KPI data in the preset time period, so that the abnormal diagnosis can be carried out on the network element before the network element fails, and the network operation and maintenance efficiency is improved.
Fig. 3 is a flowchart of a network element abnormality diagnosis method according to a second embodiment of the present invention, and as shown in fig. 3, the method includes the following steps:
step 210: and acquiring KPI data of a VNF layer target network element, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element in a preset time window to obtain test data.
Step 220: and inputting the test data into the prediction model to obtain predicted KPI data of the target network element in a preset time period.
The detailed description of step 210 to step 220 may refer to the detailed description of step 110 to step 120 in the first embodiment, and is not repeated herein.
Step 230: and calculating the error between each KPI data in the predicted KPI data of the target network element and the corresponding KPI data in the real KPI data of the target network element.
The embodiment of the invention is suitable for predicting the KPI data to be all KPI data. In this case, the error between each predicted KPI data and the corresponding actual KPI data needs to be calculated, so as to further determine whether the target network element is abnormal.
Step 240: the root mean square error of the error in a preset time period is calculated.
In this step, the KPI prediction values corresponding to each time minute in the preset time period are respectively
The actual KPI value corresponding to each minute in the preset time period is as follows:
the error between the predicted value and the true value is:
the root mean square error is used for representing the average error in a preset time period, and the calculation formula of the root mean square error is as follows:
wherein,
and
respectively representing the ith predicted KPI data and the real KPI data at the moment when the predicted time is t + a, and m representing the number of minutes included in the predicted time period.
Step 250: and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold value, determining that the target network element is abnormal.
In this step, each piece of KPI data is preset with a corresponding set threshold, where the set threshold is used to indicate a boundary where the KPI data is abnormal, and when the root mean square error of at least one piece of KPI data exceeds the corresponding set threshold, it indicates that the at least one piece of KPI data is abnormal, and the target network element is abnormal.
The embodiment of the invention determines whether the target network element is abnormal or not by determining whether the root mean square error of the target network element exceeds the corresponding set threshold value or not in the preset time period, thereby predicting the abnormality of the target network element before the target network element fails and facilitating network operation and maintenance.
Fig. 4 is a schematic structural diagram of a network element abnormality diagnosis apparatus according to a fourth embodiment of the present invention. As shown in fig. 4, the apparatus includes: the acquiring module 410 is configured to acquire KPI data of a target network element of a VNF layer within a preset time window, KPI data of a related network element related to the target network element of the VNF layer, and KPI data corresponding to the target network element of the NFVI layer, so as to obtain test data. An input module 420, configured to input the test data into a prediction model, so as to obtain predicted KPI data of the target network element within a preset time period, where the prediction model is obtained by training according to multiple sets of training data, and each set of the multiple sets of training data includes KPI data of a target network element in a VNF layer, KPI data of a related network element related to the VNF layer and the target network element, and KPI data corresponding to the NFVI layer and the target network element. An anomaly diagnosis module 430, configured to perform anomaly diagnosis on the target network element according to an error between the predicted KPI data of the target network element and the actual KPI data of the target network element.
In an optional manner, the abnormality diagnosing module 430 is further configured to calculate an error between each KPI data in the predicted KPI data of the target network element and a corresponding KPI data in the actual KPI data of the target network element; calculating the root mean square error of the error in the preset time period; and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold, determining that the target network element is abnormal.
In an alternative mode, calculating the root mean square error of the error in the preset time period includes: according to the formula
Calculating a root mean square error of the error over the preset time period, wherein,
and
respectively representing the ith predicted KPI data and the real KPI data at the moment when the predicted time is t + a, and m representing the number of minutes contained in the preset time period.
In an optional manner, the apparatus further comprises: and a building module 450 for building the LSTM neural network framework. And a normalization module 460, configured to normalize the acquired multiple sets of training data to obtain standard training data. A conversion module 470, configured to convert the dimensions of each set of training data in the standard training data into three-dimensional training data. And the training module 480 is configured to train the LSTM neural network framework according to the three-dimensional training data to obtain the prediction model.
In an optional manner, the building module 450 is further configured to build an LSTM neural network framework comprising one output layer, sixteen hidden layers and one output layer, wherein the sixteen hidden layers comprise eight LSTM layers and eight dropout layers.
In an optional manner, the training module 470 is further configured to derive weights of the LSTM neural network framework according to the plurality of sets of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a prediction model according to the weight with the minimum loss function value.
In an optional manner, the apparatus further comprises: and a verification module 490, configured to verify the prediction model according to the multiple sets of verification data. The training module 470 is further configured to retrain the prediction model when the accuracy of the plurality of sets of verification data is lower than a preset threshold.
According to the embodiment of the invention, the input module 420 is used for inputting the acquired test data into the prediction model to obtain the predicted KPI data of the target network element in the preset time period, and the abnormality diagnosis module 430 is used for carrying out abnormality diagnosis on the target network element, so that the abnormality diagnosis can be carried out on the network element before the network element fails, and the network operation and maintenance efficiency is improved.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the operation corresponding to the network element abnormity diagnosis method in any method embodiment.
An embodiment of the present invention provides a computer program product, where the computer program product includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute operations corresponding to the network element abnormality diagnosis method in any of the above-mentioned method embodiments.
Fig. 5 is a schematic structural diagram of a network element abnormality diagnosis device according to a fifth embodiment of the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the device.
As shown in fig. 5, the apparatus may include: a processor (processor) 502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with each other via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. The processor 502 is configured to execute the program 510, and may specifically execute the relevant steps in the above embodiment of the network element abnormality diagnosis method.
In particular, program 510 may include program code comprising computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement an embodiment of the invention. The network element abnormality diagnosis device comprises one or more processors, which can be processors of the same type, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
A memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to an NFVI layer and the target network element to obtain test data; inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period, wherein the prediction model is obtained by training according to multiple groups of training data, and each group of the multiple groups of training data comprises KPI data of the VNF layer target network element, KPI data of a correlated network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element; and carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: calculating the error between each KPI data in the predicted KPI data of the target network element and the corresponding KPI data in the real KPI data of the target network element; calculating the root mean square error of the error in the preset time period; and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold value, determining that the target network element is abnormal.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: and triggering an alarm device to send an abnormal alarm of the target network element to operation and maintenance personnel.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: carrying out normalization processing on the test data to obtain standard test data; inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period, wherein the predicted KPI data comprises: and inputting the standard test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: constructing an LSTM neural network framework; and training the LSTM neural network framework according to the multiple groups of training data to obtain the prediction model.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: an LSTM neural network framework is constructed that includes one output layer, sixteen hidden layers, and one output layer, where the sixteen hidden layers include eight LSTM layers and eight dropout layers.
In an alternative manner, the program 510 may be specifically configured to cause the processor 502 to perform the following operations: obtaining the weight of the LSTM neural network framework according to the multiple groups of training data; calculating a loss function value according to the weight; repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum; and obtaining a prediction model according to the weight with the minimum loss function value.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Moreover, those of skill in the art will appreciate that while some embodiments herein include some features included in other embodiments, not others, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (9)
1. A method for diagnosing network element abnormality, the method comprising:
acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to an NFVI layer and the target network element to obtain test data;
inputting the test data into a prediction model to obtain predicted KPI data of the target network element within a preset time period, wherein the prediction model is obtained by training an LSTM neural network framework according to a plurality of groups of training data, and each group of the plurality of groups of training data comprises KPI data of a VNF layer target network element, KPI data of a network element related to the VNF layer and the target network element and KPI data corresponding to a NFVI layer and the target network element; the LSTM neural network framework comprises an input layer, sixteen hidden layers and an output layer, wherein the sixteen hidden layers comprise eight LSTM layers and eight dropout layers, the eight LSTM layers and the eight dropout layers are in one-to-one correspondence, and each LSTM layer is connected with one dropout layer;
and carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
2. The method of claim 1, wherein performing an anomaly diagnosis on the target network element according to an error between the predicted KPI data of the target network element and the actual KPI data of the target network element comprises:
calculating the error between each KPI data in the predicted KPI data of the target network element and the corresponding KPI data in the real KPI data of the target network element;
calculating the root mean square error of the error in the preset time period;
and when the root mean square error of at least one item of KPI data exceeds the corresponding set threshold, determining that the target network element is abnormal.
3. The method of claim 2, wherein calculating the root mean square error of the error over the preset time period comprises:
according to the formula
Calculating a root mean square error of the error over the preset time period, wherein,
and
respectively representing the ith predicted KPI data and the real KPI data at the moment when the predicted time is t + a, and m representing the number of minutes contained in the preset time period.
4. The method of claim 1, wherein prior to obtaining test data, the method further comprises:
constructing an LSTM neural network framework;
normalizing the obtained multiple groups of training data to obtain standard training data;
converting the dimensionality of each set of training data in the standard training data into three-dimensional training data;
and training the LSTM neural network framework according to the three-dimensional training data to obtain the prediction model.
5. The method of claim 4, wherein training the LSTM neural network framework based on the plurality of sets of training data to derive the predictive model comprises:
obtaining the weight of the LSTM neural network framework according to the multiple groups of training data;
calculating a loss function value according to the weight;
repeatedly updating the weight according to an optimization algorithm until the loss function value is minimum;
and obtaining a prediction model according to the weight with the minimum loss function value.
6. The method of claim 5, wherein after deriving the predictive model, the method further comprises:
verifying the prediction model according to a plurality of groups of verification data;
and when the prediction accuracy of the multiple groups of verification data is lower than a preset threshold value, retraining the prediction model.
7. An apparatus for diagnosing network element abnormality, the apparatus comprising:
the acquisition module is used for acquiring KPI data of a VNF layer target network element in a preset time window, KPI data of a correlation network element correlated with the VNF layer and the target network element and KPI data corresponding to the NFVI layer and the target network element to obtain test data;
an input module, configured to input the test data into a prediction model, so as to obtain predicted KPI data of the target network element within a preset time period, where the prediction model is obtained by training an LSTM neural network framework according to multiple sets of training data, and each set of the multiple sets of training data includes KPI data of a target network element in a VNF layer, KPI data of a related network element related to the target network element in the VNF layer, and KPI data corresponding to the target network element in a NFVI layer; the LSTM neural network framework comprises an input layer, sixteen hidden layers and an output layer, wherein the sixteen hidden layers comprise eight LSTM layers and eight dropouts, the eight LSTM layers and the eight dropouts are in one-to-one correspondence, and each LSTM layer is connected with one dropout layer;
and the abnormity diagnosis module is used for carrying out abnormity diagnosis on the target network element according to the error between the predicted KPI data of the target network element and the real KPI data of the target network element.
8. A network element abnormality diagnostic apparatus comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction causes the processor to execute the operation corresponding to the network element abnormity diagnosis method of any one of claims 1-6.
9. A computer storage medium having at least one executable instruction stored therein, the executable instruction causing a processor to perform operations corresponding to a method for diagnosing network element abnormalities as set forth in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609173.6A CN112203311B (en) | 2019-07-08 | 2019-07-08 | Network element abnormity diagnosis method, device, equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910609173.6A CN112203311B (en) | 2019-07-08 | 2019-07-08 | Network element abnormity diagnosis method, device, equipment and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112203311A CN112203311A (en) | 2021-01-08 |
| CN112203311B true CN112203311B (en) | 2022-12-27 |
Family
ID=74004543
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910609173.6A Active CN112203311B (en) | 2019-07-08 | 2019-07-08 | Network element abnormity diagnosis method, device, equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112203311B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113608830A (en) * | 2021-07-13 | 2021-11-05 | 全球能源互联网研究院有限公司 | VNF migration method and device based on fault prediction |
| CN113988452A (en) * | 2021-11-08 | 2022-01-28 | 成都四方伟业软件股份有限公司 | Network element alarm prediction method and device based on stacked LSTM |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107783855A (en) * | 2016-08-30 | 2018-03-09 | 中兴通讯股份有限公司 | The fault self-recovery control device and method of Virtual NE |
| CN109492193A (en) * | 2018-12-28 | 2019-03-19 | 同济大学 | Abnormal network data based on depth machine learning model generate and prediction technique |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103178990A (en) * | 2011-12-20 | 2013-06-26 | 中国移动通信集团青海有限公司 | Network device performance monitoring method and network management system |
| EP2887578A1 (en) * | 2013-12-19 | 2015-06-24 | BAE Systems PLC | Network fault detection and location |
| CN103945442A (en) * | 2014-05-07 | 2014-07-23 | 东南大学 | System anomaly detection method based on linear prediction principle in mobile communication system |
| CN109150564B (en) * | 2017-06-19 | 2021-09-21 | 中国移动通信集团广东有限公司 | Prediction method and device for cell fault alarm |
| CN107819631B (en) * | 2017-11-23 | 2021-03-02 | 东软集团股份有限公司 | Equipment anomaly detection method, device and equipment |
| CN108427986A (en) * | 2018-02-26 | 2018-08-21 | 中车青岛四方机车车辆股份有限公司 | A kind of production line electrical fault prediction technique and device |
| CN108737193A (en) * | 2018-06-05 | 2018-11-02 | 亚信科技（中国）有限公司 | A kind of failure prediction method and device |
-
2019
- 2019-07-08 CN CN201910609173.6A patent/CN112203311B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107783855A (en) * | 2016-08-30 | 2018-03-09 | 中兴通讯股份有限公司 | The fault self-recovery control device and method of Virtual NE |
| CN109492193A (en) * | 2018-12-28 | 2019-03-19 | 同济大学 | Abnormal network data based on depth machine learning model generate and prediction technique |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112203311A (en) | 2021-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111124840B (en) | Method and device for predicting alarm in business operation and maintenance and electronic equipment | |
| WO2021257128A2 (en) | Quantum computing based deep learning for detection, diagnosis and other applications | |
| CN112001110B (en) | Structural damage identification monitoring method based on vibration signal space real-time recurrent graph convolutional neural network | |
| CN115115924A (en) | Concrete image crack type rapid intelligent identification method based on IR7-EC network | |
| CN113722985B (en) | Method and system for evaluating health state and predicting residual life of aero-engine | |
| Huang et al. | Machine fault detection for intelligent self-driving networks | |
| CN108919059A (en) | A kind of electric network failure diagnosis method, apparatus, equipment and readable storage medium storing program for executing | |
| CN113541985B (en) | Internet of things fault diagnosis method, model training method and related devices | |
| CN112203311B (en) | Network element abnormity diagnosis method, device, equipment and computer storage medium | |
| CN116956197B (en) | Deep learning-based energy facility fault prediction method and device and electronic equipment | |
| CN114048468A (en) | Intrusion detection method, intrusion detection model training method, device and medium | |
| CN114490065A (en) | Load prediction method, device and equipment | |
| CN113825165B (en) | 5G slice network congestion early warning method and device based on time diagram network | |
| CN113824575B (en) | Method and device for identifying fault node, computing equipment and computer storage medium | |
| CN114611372A (en) | Industrial equipment health prediction method based on Internet of things edge calculation | |
| CN114266289A (en) | Complex equipment health state assessment method | |
| CN112464990A (en) | Method and device for sensing vibration data based on current and voltage sensor | |
| CN117664558A (en) | Generator gear box abnormality detection method, device, equipment and storage medium | |
| CN116826734A (en) | Photovoltaic power generation power prediction method and device based on multi-input model | |
| CN116738169A (en) | Computer parameter anomaly prediction method and system for data dimension reduction | |
| CN115409262A (en) | Railway data center key performance index trend prediction method and abnormity identification method | |
| CN112242959B (en) | Micro-service current-limiting control method, device, equipment and computer storage medium | |
| CN114564877A (en) | Rolling bearing service life prediction method, system, equipment and readable storage medium | |
| CN112199977A (en) | Communication machine room abnormity detection method and device and computing equipment | |
| CN110826690A (en) | Equipment state identification method and system and computer readable 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 |