CN113852507A - Method, system, equipment and storage medium for predicting network health state - Google Patents
Method, system, equipment and storage medium for predicting network health state Download PDFInfo
- Publication number
- CN113852507A CN113852507A CN202111148252.5A CN202111148252A CN113852507A CN 113852507 A CN113852507 A CN 113852507A CN 202111148252 A CN202111148252 A CN 202111148252A CN 113852507 A CN113852507 A CN 113852507A
- Authority
- CN
- China
- Prior art keywords
- network
- state
- model
- prediction
- time sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000036541 health Effects 0.000 title claims abstract description 29
- 238000003066 decision tree Methods 0.000 claims abstract description 34
- 238000003062 neural network model Methods 0.000 claims abstract description 23
- 230000000306 recurrent effect Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 18
- 238000010606 normalization Methods 0.000 claims abstract description 17
- 230000004044 response Effects 0.000 claims abstract description 16
- 230000003862 health status Effects 0.000 claims description 23
- 230000006870 function Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 9
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 125000004122 cyclic group Chemical group 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 238000012549 training Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 3
- 206010033799 Paralysis Diseases 0.000 description 2
- 230000004913 activation Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000014509 gene expression Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1097—Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
Abstract
The invention provides a method, a system, equipment and a storage medium for predicting the health state of a network, wherein the method comprises the following steps: acquiring time sequence state data of multiple dimensions in a network, and carrying out normalization processing on the time sequence state data of the multiple dimensions; sending the time sequence state data after normalization processing into a recurrent neural network model to extract effective characteristics of a network state; predicting a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and predicting the network health state of the current network port according to the prediction model, and giving an alarm and switching the network port in response to the prediction result being in the sub-health state. According to the invention, the state of the network is predicted by combining the recurrent neural network and the decision tree model through the time sequence state data of the network, the accuracy is higher, and the stability and the reliability of the system are improved.
Description
Technical Field
The present invention relates to the field of distributed storage systems, and more particularly, to a method, system, device, and storage medium for predicting a health status of a network.
Background
The state that the network can normally operate and can be quickly recovered after being impacted by the outside is called as a 'healthy' state; the state of being paralyzed and failing to operate normally is called "unhealthy" state. Many large and medium-sized enterprises have their networks in a "sub-healthy" state. The network in this state can normally operate at ordinary times, but the capability of resisting risks is extremely low, the network is easy to fall into paralysis under the condition of sudden network risks, the network is difficult to recover for a long time, and the overall performance of the cluster is seriously influenced. Therefore, it is necessary to predict in advance whether the current network state will become a sub-health state, and most of the prior art collects message information of network communication and directly judges the transmitted message information, and cannot predict the network state in real time.
Disclosure of Invention
In view of this, an object of an embodiment of the present invention is to provide a method, a system, a computer device, and a computer readable storage medium for predicting a network health state, in which network state data of different characteristics at different times are collected as training sample data, the training sample data is sorted and processed, the sample data is input into a recurrent neural network model for feature extraction, the extracted features are calculated and predicted by a decision tree model, and after an output prediction result is compared with a set threshold, the network state of a storage system can be classified into "healthy" and "sub-healthy" 2 categories, so that the network state can be predicted in real time, the accuracy is higher, and the stability and reliability of the system are improved.
Based on the above object, an aspect of the embodiments of the present invention provides a method for predicting a network health status, including the following steps: acquiring time sequence state data of multiple dimensions in a network, and carrying out normalization processing on the time sequence state data of the multiple dimensions; sending the time sequence state data after normalization processing into a recurrent neural network model to extract effective characteristics of a network state; predicting a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and predicting the network health state of the current network port according to the prediction model, and giving an alarm and switching the network port in response to the prediction result being in the sub-health state.
In some embodiments, the sending the normalized time-series state data into the recurrent neural network model to extract the network state valid features includes: the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
In some embodiments, the normalizing the time-series state data of the plurality of dimensions includes: and marking the corresponding network state label for the time sequence state data of each dimension.
In some embodiments, the predicting the network health state of the distributed storage system using the decision tree model in combination with the network state valid features to form a prediction model comprises: judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and in response to the prediction result output by the decision tree model being greater than a preset threshold, marking the network state as a sub-health state.
In another aspect of the embodiments of the present invention, a system for predicting a network health status is provided, including: the acquisition module is configured to acquire time sequence state data of multiple dimensions in a network and normalize the time sequence state data of the multiple dimensions; the extraction module is configured to send the time sequence state data after the normalization processing into the recurrent neural network model to extract the effective characteristics of the network state; a prediction module configured to predict a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and the execution module is configured to predict the network health state of the current network port according to the prediction model, and perform alarm and switch the network port in response to the prediction result being in the sub-health state.
In some embodiments, the extraction module is configured to: the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
In some embodiments, the acquisition module is configured to: and marking the corresponding network state label for the time sequence state data of each dimension.
In some embodiments, the prediction module is configured to: judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and in response to the prediction result output by the decision tree model being greater than a preset threshold, marking the network state as a sub-health state.
In another aspect of the embodiments of the present invention, there is also provided a computer device, including: at least one processor; and a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method as above.
In a further aspect of the embodiments of the present invention, a computer-readable storage medium is also provided, in which a computer program for implementing the above method steps is stored when the computer program is executed by a processor.
The invention has the following beneficial technical effects: by collecting network state data with different characteristics at different time as training sample data, the sample data is input into a recurrent neural network model after being sorted and processed to extract the characteristics, then the extracted characteristics are calculated and predicted through a decision tree model, and after an output prediction result is compared with a set threshold value, the network state of the storage system can be divided into 2 categories of 'healthy' and 'sub-healthy', so that the network state can be predicted, the network state can be predicted in real time, the accuracy is higher, and the stability and the reliability of the system are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other embodiments can be obtained by using the drawings without creative efforts.
FIG. 1 is a diagram illustrating an embodiment of a method for predicting a health status of a network according to the present invention;
FIG. 2 is a diagram illustrating an embodiment of a system for predicting a health status of a network according to the present invention;
FIG. 3 is a schematic hardware diagram of an embodiment of a computer device for predicting a health status of a network according to the present invention;
FIG. 4 is a schematic diagram of an embodiment of a computer storage medium for predicting a health status of a network provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the following embodiments of the present invention are described in further detail with reference to the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
In a first aspect of an embodiment of the present invention, an embodiment of a method for predicting a network health status is provided. Fig. 1 is a schematic diagram illustrating an embodiment of a method for predicting a health status of a network according to the present invention. As shown in fig. 1, the embodiment of the present invention includes the following steps:
s1, acquiring time sequence state data of multiple dimensions in the network, and carrying out normalization processing on the time sequence state data of the multiple dimensions;
s2, sending the time sequence state data after normalization processing into a recurrent neural network model to extract effective characteristics of the network state;
s3, predicting the network health state of the distributed storage system by using a decision tree model and combining the network state effective characteristics to form a prediction model; and
and S4, predicting the network health state of the current internet access according to the prediction model, and giving an alarm and switching the internet access in response to the prediction result being in a sub-health state.
According to the embodiment of the invention, network transmission time sequence state data of a distributed storage system network under read-write services and the like are obtained, the time sequence state data comprise network time delay, network packet loss rate and network bandwidth utilization rate, effective characteristics of the time sequence state data are extracted by using a recurrent neural network, then the health state of the storage system network is predicted by using a decision tree model, and when the storage system network state is judged to be sub-health, the storage system alarms the sub-health network and switches to a healthy network port.
The method comprises the steps of obtaining time sequence state data of multiple dimensions in a network, and carrying out normalization processing on the time sequence state data of the multiple dimensions.
In some embodiments, the normalizing the time-series state data of the plurality of dimensions includes: and marking the corresponding network state label for the time sequence state data of each dimension.
Collecting time sequence state data of a storage system network under a service as training sample data, wherein the data are respectively network time delay, network packet loss rate and network bandwidth utilization rate; and (3) carrying out normalization processing on the time sequence state data of the 3 dimensions to obtain training sample data with the dimension i x j x 3, and marking a corresponding network state label, thereby obtaining the training sample data and the label related to the network state of the storage system. The one-dimensional training samples obtained can be represented as:
wherein, F represents the obtained training sample, n takes a value of 1-3, which can be expressed as network time delay, network packet loss rate and network bandwidth utilization rate, and Xi(t) may be expressed as a timing state training sample, [ x ] acquired for the ith nodei1 xi2 ... xij]And acquiring the time sequence state characteristics of the network ports at j moments for the ith storage node.
And sending the time sequence state data after the normalization processing into a recurrent neural network model to extract the effective characteristics of the network state.
And the acquired time sequence state data is sent to a recurrent neural network for effective feature extraction after normalization processing. For a recurrent neural network, comprising an input layer, a hidden layer and an output layer, the activation function of the hidden layer is denoted as f (),
the computation of the hidden layer can be expressed as:
st＝f(wXi(t)+ust-1)
where w and u are represented as a weight matrix, stRepresenting the output of the hidden layer at time t.
Representing the activation function of the output layer as h (), the computation of the output layer can be expressed as:
ot＝h(vst)
where v is represented as a weight matrix, otRepresented as the output of the output layer.
In some embodiments, the sending the normalized time-series state data into the recurrent neural network model to extract the network state valid features includes: the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
Predicting a network health state of the distributed storage system using a decision tree model in conjunction with the network state valid features to form a prediction model.
And (2) utilizing time sequence data of the network state of the storage system, inputting the extracted effective characteristics of the network state into CART for prediction, wherein the decision tree model is simply expressed as T (), and the network state output by the decision tree model is as follows:
nt＝T(ot)
where nt represents the network state of the output.
In some embodiments, the predicting the network health state of the distributed storage system using the decision tree model in combination with the network state valid features to form a prediction model comprises: judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and in response to the prediction result output by the decision tree model being greater than a preset threshold, marking the network state as a sub-health state.
And predicting the network health state of the current network port according to the prediction model, and giving an alarm and switching the network port in response to the prediction result of the sub-health state. And applying the trained model to a storage system to predict the network state, if the network state of the storage system is predicted and marked as a sub-health state, the storage system gives an alarm to the network in the sub-health state, the alarm information comprises the specific state of the sub-health state of the network and network port information, and then the storage system switches the corresponding sub-health network port to the health network port.
According to the embodiment of the invention, the network state data of different characteristics at different time are collected as training sample data, the sample data is input into the recurrent neural network model after being sorted and processed to carry out characteristic extraction, then the extracted characteristics are calculated and predicted through the decision tree model, and the output prediction result is compared with the set threshold value, so that the network state is predicted in real time, the accuracy is higher, and the stability and the reliability of the system are improved.
It should be particularly noted that, the steps in the embodiments of the method for predicting the network health status described above may be mutually intersected, replaced, added, or deleted, and therefore, these methods for predicting the network health status that are transformed by reasonable permutation and combination should also belong to the scope of the present invention, and should not limit the scope of the present invention to the embodiments.
In view of the above, according to a second aspect of the embodiments of the present invention, a system for predicting a health status of a network is provided. As shown in fig. 2, the system 200 includes the following modules: the acquisition module is configured to acquire time sequence state data of multiple dimensions in a network and normalize the time sequence state data of the multiple dimensions; the extraction module is configured to send the time sequence state data after the normalization processing into the recurrent neural network model to extract the effective characteristics of the network state; a prediction module configured to predict a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and the execution module is configured to predict the network health state of the current network port according to the prediction model, and perform alarm and switch the network port in response to the prediction result being in the sub-health state.
In some embodiments, the extraction module is configured to: the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
In some embodiments, the acquisition module is configured to: and marking the corresponding network state label for the time sequence state data of each dimension.
In some embodiments, the prediction module is configured to: judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and in response to the prediction result output by the decision tree model being greater than a preset threshold, marking the network state as a sub-health state.
In view of the above object, a third aspect of the embodiments of the present invention provides a computer device, including: at least one processor; and a memory storing computer instructions executable on the processor, the instructions being executable by the processor to perform the steps of: s1, acquiring time sequence state data of multiple dimensions in the network, and carrying out normalization processing on the time sequence state data of the multiple dimensions; s2, sending the time sequence state data after normalization processing into a recurrent neural network model to extract effective characteristics of the network state; s3, predicting the network health state of the distributed storage system by using a decision tree model and combining the network state effective characteristics to form a prediction model; and S4, predicting the network health state of the current internet access according to the prediction model, and giving an alarm and switching the internet access in response to the prediction result being in the sub-health state.
In some embodiments, the sending the normalized time-series state data into the recurrent neural network model to extract the network state valid features includes: the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
In some embodiments, the normalizing the time-series state data of the plurality of dimensions includes: and marking the corresponding network state label for the time sequence state data of each dimension.
In some embodiments, the predicting the network health state of the distributed storage system using the decision tree model in combination with the network state valid features to form a prediction model comprises: judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and in response to the prediction result output by the decision tree model being greater than a preset threshold, marking the network state as a sub-health state.
Fig. 3 is a schematic hardware structural diagram of an embodiment of the computer device for predicting the network health status provided by the present invention.
Taking the device shown in fig. 3 as an example, the device includes a processor 301 and a memory 302.
The processor 301 and the memory 302 may be connected by a bus or other means, such as the bus connection in fig. 3.
The memory 302 is a non-volatile computer-readable storage medium and can be used for storing non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the method for predicting the health status of the network in the embodiment of the present application. The processor 301 executes various functional applications of the server and data processing, i.e., implements a method of predicting a health status of a network, by executing nonvolatile software programs, instructions, and modules stored in the memory 302.
The memory 302 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to use of a method of predicting a health state of a network, and the like. Further, the memory 302 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 302 optionally includes memory located remotely from processor 301, which may be connected to a local module via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
One or more methods of predicting a health status of a network corresponding computer instructions 303 are stored in the memory 302 that, when executed by the processor 301, perform the method of predicting a health status of a network in any of the method embodiments described above.
Any embodiment of a computer device implementing the method for predicting a health status of a network as described above may achieve the same or similar effects as any of the preceding method embodiments corresponding thereto.
The present invention also provides a computer readable storage medium storing a computer program which, when executed by a processor, performs a method of predicting a health status of a network.
Fig. 4 is a schematic diagram of an embodiment of a computer storage medium for predicting a network health status according to the present invention. Taking the computer storage medium as shown in fig. 4 as an example, the computer readable storage medium 401 stores a computer program 402 which, when executed by a processor, performs the method as described above.
Finally, it should be noted that, as one of ordinary skill in the art can appreciate that all or part of the processes of the methods of the above embodiments can be implemented by a computer program to instruct related hardware, and the program of the method for predicting the health status of the network can be stored in a computer readable storage medium, and when executed, the program can include the processes of the embodiments of the methods as described above. The storage medium of the program may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like. The embodiments of the computer program may achieve the same or similar effects as any of the above-described method embodiments.
The foregoing is an exemplary embodiment of the present disclosure, but it should be noted that various changes and modifications could be made herein without departing from the scope of the present disclosure as defined by the appended claims. The functions, steps and/or actions of the method claims in accordance with the disclosed embodiments described herein need not be performed in any particular order. Furthermore, although elements of the disclosed embodiments of the invention may be described or claimed in the singular, the plural is contemplated unless limitation to the singular is explicitly stated.
It should be understood that, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly supports the exception. It should also be understood that "and/or" as used herein is meant to include any and all possible combinations of one or more of the associated listed items.
The numbers of the embodiments disclosed in the embodiments of the present invention are merely for description, and do not represent the merits of the embodiments.
It will be understood by those skilled in the art that all or part of the steps for implementing the above embodiments may be implemented by hardware, or may be implemented by a program instructing relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, etc.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, of embodiments of the invention is limited to these examples; within the idea of an embodiment of the invention, also technical features in the above embodiment or in different embodiments may be combined and there are many other variations of the different aspects of the embodiments of the invention as described above, which are not provided in detail for the sake of brevity. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present invention are intended to be included within the scope of the embodiments of the present invention.
Claims (10)
1. A method of predicting a health status of a network, comprising the steps of:
acquiring time sequence state data of multiple dimensions in a network, and carrying out normalization processing on the time sequence state data of the multiple dimensions;
sending the time sequence state data after normalization processing into a recurrent neural network model to extract effective characteristics of a network state;
predicting a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and
and predicting the network health state of the current network port according to the prediction model, and giving an alarm and switching the network port in response to the prediction result of the sub-health state.
2. The method of claim 1, wherein the step of sending the normalized time-series state data into the recurrent neural network model to extract the network state valid features comprises the following steps:
the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
3. The method of claim 1, wherein normalizing the time series state data of the plurality of dimensions comprises:
and marking the corresponding network state label for the time sequence state data of each dimension.
4. The method of claim 1, wherein the predicting the network health state of the distributed storage system using the decision tree model in combination with the network state validity characteristic to form a prediction model comprises:
judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and
and in response to the prediction result output by the decision tree model being larger than a preset threshold value, marking the network state as a sub-health state.
5. A system for predicting a health status of a network, comprising:
the acquisition module is configured to acquire time sequence state data of multiple dimensions in a network and normalize the time sequence state data of the multiple dimensions;
the extraction module is configured to send the time sequence state data after the normalization processing into the recurrent neural network model to extract the effective characteristics of the network state;
a prediction module configured to predict a network health state of the distributed storage system using a decision tree model in combination with the network state validity features to form a prediction model; and
and the execution module is configured to predict the network health state of the current network port according to the prediction model, and perform alarm and switch the network port in response to the prediction result being in the sub-health state.
6. The system of claim 5, wherein the extraction module is configured to:
the iteration number of the cyclic neural network model is set to be 50, the window length used for prediction is set to be 6, the number of full-connection layers is set to be 3, the number of hidden nodes is set to be 12, the mean square error is used as a loss function, and the adam algorithm is selected as an optimizer.
7. The system of claim 5, wherein the acquisition module is configured to:
and marking the corresponding network state label for the time sequence state data of each dimension.
8. The system of claim 5, wherein the prediction module is configured to:
judging whether the prediction result output by the decision tree model is larger than a preset threshold value or not; and
and in response to the prediction result output by the decision tree model being larger than a preset threshold value, marking the network state as a sub-health state.
9. A computer device, comprising:
at least one processor; and
a memory storing computer instructions executable on the processor, the instructions when executed by the processor implementing the steps of the method of any one of claims 1 to 4.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111148252.5A CN113852507A (en) | 2021-09-29 | 2021-09-29 | Method, system, equipment and storage medium for predicting network health state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111148252.5A CN113852507A (en) | 2021-09-29 | 2021-09-29 | Method, system, equipment and storage medium for predicting network health state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113852507A true CN113852507A (en) | 2021-12-28 |
Family
ID=78976919
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111148252.5A Pending CN113852507A (en) | 2021-09-29 | 2021-09-29 | Method, system, equipment and storage medium for predicting network health state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113852507A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200136975A1 (en) * | 2018-10-26 | 2020-04-30 | Hughes Network Systems, Llc | Monitoring a communication network |
| CN111884870A (en) * | 2020-06-28 | 2020-11-03 | 苏州浪潮智能科技有限公司 | Method, device, terminal and storage medium for predicting network sub-health state |
| CN112577747A (en) * | 2020-12-07 | 2021-03-30 | 东南大学 | Rolling bearing fault diagnosis method based on space pooling network |
| CN113190405A (en) * | 2021-04-29 | 2021-07-30 | 山东英信计算机技术有限公司 | Node health detection method and device, electronic equipment and storage medium |
-
2021
- 2021-09-29 CN CN202111148252.5A patent/CN113852507A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200136975A1 (en) * | 2018-10-26 | 2020-04-30 | Hughes Network Systems, Llc | Monitoring a communication network |
| CN111884870A (en) * | 2020-06-28 | 2020-11-03 | 苏州浪潮智能科技有限公司 | Method, device, terminal and storage medium for predicting network sub-health state |
| CN112577747A (en) * | 2020-12-07 | 2021-03-30 | 东南大学 | Rolling bearing fault diagnosis method based on space pooling network |
| CN113190405A (en) * | 2021-04-29 | 2021-07-30 | 山东英信计算机技术有限公司 | Node health detection method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110784481B (en) | DDoS detection method and system based on neural network in SDN network | |
| Hsieh et al. | Detection DDoS attacks based on neural-network using Apache Spark | |
| US10200382B2 (en) | System and method for detecting abnormal traffic behavior using infinite decaying clusters | |
| CN113015167B (en) | Encrypted flow data detection method, system, electronic device and storage medium | |
| Ortet Lopes et al. | Towards effective detection of recent DDoS attacks: A deep learning approach | |
| CN112822189A (en) | Traffic identification method and device | |
| CN109347853B (en) | Deep packet analysis-based anomaly detection method for integrated electronic system | |
| CN111600919A (en) | Web detection method and device based on artificial intelligence | |
| CN114124503B (en) | Intelligent network sensing method for optimizing efficiency of progressive concurrent cache | |
| CN115237717A (en) | Micro-service abnormity detection method and system | |
| CN113742718B (en) | Industrial Internet equipment attack path restoration method, related equipment and system | |
| CN113282920B (en) | Log abnormality detection method, device, computer equipment and storage medium | |
| CN113938290A (en) | Website de-anonymization method and system for user side traffic data analysis | |
| CN111447169B (en) | Method and system for identifying malicious webpage in real time on gateway | |
| CN113852507A (en) | Method, system, equipment and storage medium for predicting network health state | |
| CN115567305A (en) | Sequential network attack prediction analysis method based on deep learning | |
| CN114116853A (en) | Data security analysis method and device based on time sequence correlation analysis | |
| CN113298125A (en) | Internet of things equipment flow abnormity detection method and device based on feature selection and storage medium | |
| CN114979017B (en) | Deep learning protocol identification method and system based on original flow of industrial control system | |
| Qiu et al. | Abnormal Traffic Detection Method of Internet of Things Based on Deep Learning in Edge Computing Environment | |
| Staudemeyer et al. | Feature set reduction for automatic network intrusion detection with machine learning algorithms | |
| Benova et al. | Web server load prediction and anomaly detection from hypertext transfer protocol logs. | |
| CN113098886B (en) | Protection operation service configuration method based on artificial intelligence and block chain system | |
| CN112187498B (en) | Bypass protection method, device and system thereof and Deep Packet Inspection (DPI) system | |
| Mahmood et al. | Securing IOT against DDOS attacks using machine learning |
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 |