CN115022210A - Construction method, prediction method and device of network traffic prediction model - Google Patents
Construction method, prediction method and device of network traffic prediction model Download PDFInfo
- Publication number
- CN115022210A CN115022210A CN202210883364.3A CN202210883364A CN115022210A CN 115022210 A CN115022210 A CN 115022210A CN 202210883364 A CN202210883364 A CN 202210883364A CN 115022210 A CN115022210 A CN 115022210A
- Authority
- CN
- China
- Prior art keywords
- network traffic
- data
- network
- traffic data
- network flow
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000010276 construction Methods 0.000 title abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 37
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 18
- 238000004590 computer program Methods 0.000 claims description 29
- 238000012795 verification Methods 0.000 claims description 22
- 238000003860 storage Methods 0.000 claims description 15
- 238000000605 extraction Methods 0.000 claims description 10
- 238000011156 evaluation Methods 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 6
- 238000010200 validation analysis Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 11
- 230000006870 function Effects 0.000 description 18
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 10
- 238000004891 communication Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 230000009131 signaling function Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- 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
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to a construction method, a prediction method and a prediction device of a network traffic prediction model. The method comprises the steps of obtaining historical network flow data arranged according to a time sequence; performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data; performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence; extracting the characteristics of the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple characteristics; and inputting the plurality of characteristics as training samples into the extreme learning model for training to obtain the network flow prediction model. By the embodiment of the invention, the accuracy of the network flow prediction is improved, the problem of low accuracy of the network flow prediction in the prior art is solved, and data support is provided for network service quality guarantee and the like.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a construction method, a prediction method and a prediction device of a network traffic prediction model.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The methods used for predicting the network traffic at present have certain network traffic prediction capability. Although having some characteristics and advantages, there are some defects and deficiencies, such as the linear regression model cannot accurately describe the network traffic change characteristics, the application range is limited, and the optimal network traffic prediction effect is difficult to achieve under the condition of a large-scale data set; the parameters of the support vector machine have great influence on the learning and generalization capability; the defect of long training time of the extreme learning machine exists; the clustering model is mainly oriented to the situation that the time distribution difference of network traffic data is large, such as the situation that traffic is crowded in a local peak transaction situation and parts of other time periods are idle.
At present, a method for constructing a network traffic prediction model and a prediction method are needed, so that the problem of low accuracy of network traffic prediction in the prior art is solved.
Disclosure of Invention
In order to solve the problems in the prior art, embodiments of the present invention provide a method for constructing a network traffic prediction model, a prediction method, and a device, which can be applied to a current rapidly-developed and high-demand network traffic prediction scenario, improve the accuracy of network traffic prediction, solve the problem of low accuracy of network traffic prediction in the prior art, and provide data support for network quality of service guarantee and the like.
In order to solve the technical problems, the specific technical scheme of the invention is as follows:
in one aspect, an embodiment of the present invention provides a method for constructing a network traffic model, where the method includes:
acquiring historical network flow data arranged according to a time sequence;
performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data;
performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence;
extracting the characteristics of the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple characteristics;
and inputting the plurality of characteristics as training samples into an extreme learning model for training to obtain a network flow prediction model.
Further, extracting the characteristics of the historical network flow data according to the nonlinear network flow sub-sequence to obtain a plurality of characteristics,
and according to the time sequence of the historical network flow data, data corresponding to the nonlinear network flow subsequences in the historical network flow data are taken from back to front to obtain the multiple features.
Further, using the features as training samples further comprises,
and performing cluster analysis on the plurality of features, and taking the result of the cluster analysis as the training sample.
Further, after obtaining the network traffic prediction model, the method further comprises,
and optimizing the network traffic prediction model by taking the traffic data comprising the preset characteristics as a model verification sample.
Further, using traffic data including predetermined characteristics as model validation samples, optimizing the network traffic prediction model further comprises,
calculating the model verification sample by using the network traffic prediction model to obtain a prediction result corresponding to the model verification sample;
calculating the difference and variance of the prediction result and the actual value of the model verification sample;
and optimizing the network flow prediction model by taking the difference value and the variance as prediction error evaluation indexes and taking the minimum prediction error as a decision condition.
On the other hand, an embodiment of the present invention further provides a device for constructing a network traffic prediction model, including:
the historical network flow data acquisition unit is used for acquiring historical network flow data arranged according to a time sequence;
the wavelet decomposition unit is used for performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data;
the phase space reconstruction unit is used for performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence;
a feature extraction unit, configured to perform feature extraction on the historical network traffic data according to the nonlinear network traffic sub-sequence, and use the extracted multiple pieces of network traffic data as multiple features;
and the model training unit is used for inputting the plurality of characteristics as training samples into the extreme learning model for training to obtain the network traffic prediction model.
Based on the same invention concept, the embodiment of the invention also provides a method for predicting network traffic, which comprises the steps of obtaining current network traffic data;
the network traffic prediction model constructed according to the construction method of the network traffic prediction model calculates the current network traffic data to obtain the network traffic data after the current network traffic data, so as to evaluate the future network service quality according to the calculated network traffic data.
On the other hand, an embodiment of the present invention further provides a device for predicting network traffic, including:
a current network traffic data obtaining unit, configured to obtain current network traffic data;
and the future network flow data calculation unit is used for calculating the current network flow data according to the network flow prediction model constructed by the construction method of the network flow prediction model to obtain the network flow data behind the current network flow data so as to evaluate the future network service quality according to the calculated network flow data.
In another aspect, an embodiment of the present invention further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the above method when executing the computer program.
In another aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the above method.
Finally, an embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and the computer program is executed by a processor to implement the method.
In the embodiment of the invention, the historical network flow data sorted according to the time sequence is firstly obtained, then the wavelet decomposition is carried out on the historical network flow data to obtain the multi-scale component of the historical network flow data, so that the historical network flow data is decomposed according to the multi-scale frequency, the decomposed network flow component does not have the multi-scale frequency any more, the complexity of flow prediction is greatly reduced, and the influence of the multi-scale frequency on the accuracy of the prediction result is effectively reduced. And then, carrying out phase space reconstruction on the multi-scale component obtained after decomposition to obtain a nonlinear network flow quantum sequence, then carrying out feature extraction on the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple features, so that a shorter time sequence capable of reflecting the system rule is extracted from a longer time sequence, and the nonlinear network flow quantum sequence can reflect the shorter time sequence of the network system rule, thereby reducing the calculation amount. And finally, inputting the plurality of characteristics as training samples into an extreme learning model for training to obtain a network flow prediction model, wherein the extreme learning model only needs to set a proper number of hidden layer nodes to randomly generate all parameters required by a hidden layer compared with the traditional neural network learning algorithm, and determines the weight of an output layer by using a least square method, the whole learning process only needs one step without updating the hidden layer parameters for many times, so that the method has strong fast learning capability and strong nonlinear approximation capability. By the method, the accuracy of the network flow prediction is improved, and the problem of low accuracy of the network flow prediction in the prior art is solved. The method provided by the embodiment of the invention can be suitable for the current rapidly-developed and high-requirement network flow prediction scene, and provides data support for network service quality guarantee and the like. The network flow prediction can also identify the possible abnormal flow situation in advance, perform advance evaluation according to the flow prediction model, identify risks in advance, and avoid the problems of network service quality reduction or network unavailability and the like.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. In the drawings:
fig. 1 is a schematic diagram of an implementation system of a method for constructing a network traffic prediction model according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for constructing a network traffic prediction model according to an embodiment of the present invention;
fig. 3 is a process of optimizing a network traffic prediction model by using traffic data including predetermined characteristics as a model verification sample according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a device for constructing a network traffic prediction model according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a method for predicting network traffic according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a device for predicting network traffic according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present invention.
Description of the symbols of the drawings:
101. a terminal;
102. a server;
401. a historical network traffic data acquisition unit;
402. a wavelet decomposition unit;
403. a phase space reconstruction unit;
404. a feature extraction unit;
405. a model training unit;
601. a current network traffic data acquisition unit;
602. a future network flow data calculation unit;
702. a computer device;
704. a processing device;
706. a storage resource;
708. a drive mechanism;
710. an input/output module;
712. an input device;
714. an output device;
716. a presentation device;
718. a graphical user interface;
720. a network interface;
722. a communication link;
724. a communication bus.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, apparatus, article, or device that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or device.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer-executable instructions and that, although a logical order is illustrated in the flowcharts, in some cases, the steps illustrated or described may be performed in an order different than presented herein.
Fig. 1 is a schematic diagram of an implementation system of a method for constructing a network traffic prediction model according to an embodiment of the present invention, which may include: a terminal 101 and a server 102, wherein the terminal 101 and the server 102 communicate with each other through a Network, and the Network may include a Local Area Network (LAN), a Wide Area Network (WAN), the internet, or a combination thereof, and is connected to a website, a user device (e.g., a computing device), and a backend system. When the network traffic prediction model is constructed, the terminal 101 may input historical network traffic data to the server 102, and the server 102 may analyze and process the historical network traffic data input by the terminal 101 to obtain a plurality of network traffic data as a plurality of features, and input the plurality of features as training samples into the extreme learning model for training to obtain the network traffic prediction model. When the network traffic needs to be predicted, the terminal 101 inputs current network traffic data to the server 102, the server 102 calculates the current network traffic data by using the trained network traffic prediction model to obtain network traffic data after the current network traffic data, and then sends the calculated network traffic data to the terminal 101. Wherein a processor that processes network traffic data may be deployed on server 102. Alternatively, the processors may be nodes of a cloud computing system (not shown), or each processor may be a separate cloud computing system, comprising multiple computers interconnected by a network and operating as a distributed processing system.
In addition, it should be noted that fig. 1 is only one application environment provided by the present disclosure, and in practical applications, a plurality of terminals 101 may also be included, and this specification is not limited.
Specifically, the implementation of the invention provides a method for constructing a network traffic prediction model, which can be applied to the current rapidly-developed and high-requirement network traffic prediction scene. Fig. 2 is a flow chart of a method for constructing a network traffic prediction model according to an embodiment of the present invention, in which a process of constructing a network traffic prediction model is described, but more or fewer operation steps may be included based on conventional or non-inventive labor. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual system or apparatus product executes, it can execute sequentially or in parallel according to the method shown in the embodiment or the figures. As shown in fig. 2, the method may be performed by the server 102, and may include:
step 201: acquiring historical network flow data arranged according to a time sequence;
step 202: performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data;
step 203: performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence;
step 204: extracting the characteristics of the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple characteristics;
step 205: and inputting the plurality of characteristics as training samples into an extreme learning model for training to obtain a network flow prediction model.
In the embodiment of the invention, the historical network flow data sorted according to the time sequence is firstly obtained, then the wavelet decomposition is carried out on the historical network flow data to obtain the multi-scale component of the historical network flow data, so that the historical network flow data is decomposed according to the multi-scale frequency, the decomposed network flow component does not have the multi-scale frequency any more, the complexity of flow prediction is greatly reduced, and the influence of the multi-scale frequency on the accuracy of the prediction result is effectively reduced. And then, carrying out phase space reconstruction on the multi-scale component obtained after decomposition to obtain a nonlinear network flow quantum sequence, then carrying out feature extraction on the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple features, so that a shorter time sequence capable of reflecting the system rule is extracted from a longer time sequence, and the nonlinear network flow quantum sequence can reflect the shorter time sequence of the network system rule, thereby reducing the calculation amount. And finally, inputting the plurality of characteristics as training samples into an extreme learning model for training to obtain a network flow prediction model, wherein the extreme learning model only needs to set a proper number of hidden layer nodes to randomly generate all parameters required by a hidden layer, and determines the weight of an output layer by using a least square method, and the whole learning process only needs one step without updating the hidden layer parameters for multiple times, so that the extreme learning model has strong fast learning capability and strong nonlinear approximation capability. By the method, the accuracy of the network flow prediction is improved, and the problem of low accuracy of the network flow prediction in the prior art is solved. The method provided by the embodiment of the invention can be suitable for the current rapidly-developed and high-requirement network flow prediction scene, and provides data support for network service quality guarantee and the like. The network flow prediction can also identify the possible abnormal flow situation in advance, perform advance evaluation according to the flow prediction model, identify risks in advance, and avoid the problems of network service quality reduction or network unavailability and the like.
In the embodiment of the invention, the network flow time sequence is a nonlinear multi-time scale transformation power system and has the characteristics of obvious self-similarity, burst property, periodicity and the like. Therefore, in the practical application scenario, the complexity of the network traffic change affects the accuracy of the network traffic prediction, especially under the condition that the network traffic itself has multi-scale frequency, and cannot meet the requirement of network transmission, therefore, the invention performs wavelet decomposition on the historical network traffic data, the wavelet decomposition is to expand the original network traffic data according to the designated wavelet function cluster, that is, the original network traffic data is represented as a series of linear combinations of wavelet functions with different scales and different time shifts, wherein the coefficient of each term is called as a wavelet coefficient, and the linear combination of all the wavelet functions with different time shifts under the same scale is called as a wavelet component of the network traffic data under the scale, because the network traffic data is discrete data, the wavelet function is not an orthogonal function, the wavelet transformation needs a scale function, that is, the original signal function can be decomposed into the linear combination of the scale function and the wavelet function, in this function, the scale function generates a low frequency part, and the wavelet function generates a high frequency part, so that the wavelet coefficients include detail coefficients corresponding to the high frequency part in the flow time series data and approximation coefficients corresponding to the low frequency part. And performing wavelet decomposition on the historical network flow data through a wavelet function and a scale function to obtain a multi-scale component.
And then carrying out phase space reconstruction on the obtained multi-scale components to obtain a nonlinear network flow subsequence. Specifically, most network traffic data have chaotic characteristics, the chaotic characteristics can use a Lyapunov exponent as a criterion, when the Lyapunov exponent is less than 0, the time series change is stable, when the Lyapunov exponent is equal to 0, the time series change is at a stable boundary, and when the Lyapunov exponent is greater than 0, the time series change is unstable. The phase space reconstruction method is a common method for researching the chaos structure, can extract a shorter time sequence capable of reflecting the system rule from a longer time sequence, and can reflect a shorter time sequence of the network system rule by a nonlinear network flow quantum sequence, so that the calculation amount is reduced.
And then extracting the characteristics of the historical network flow data according to the nonlinear network flow subsequence obtained by phase space reconstruction, taking the extracted multiple network flow data as multiple characteristics, and taking the nonlinear network flow subsequence as an optimal historical data length, so that the data is extracted from the historical network flow according to the optimal data length, and then taking the optimal historical network data as a training sample, inputting the optimal historical network data into a limit learning model, and training to obtain a network flow prediction model. It can be understood that obtaining the optimal historical data length can improve the accuracy and the operational efficiency of the network traffic prediction.
According to an embodiment of the invention, performing feature extraction on the historical network traffic data according to the non-linear network traffic sub-sequence, obtaining a plurality of features further comprises,
and according to the time sequence of the historical network flow data, data corresponding to the nonlinear network flow subsequences in the historical network flow data are taken from back to front to obtain the multiple features.
Illustratively, by using an aggregation variance method or a re-standard polar difference analysis (R/S analysis), the Hurst parameter of historical network traffic data is calculated, a data self-similarity feature is obtained, and the obtained data self-similarity feature is used as a plurality of features.
In an embodiment of the present invention, there may be a certain similarity between the optimal historical network data, therefore, in order to further reduce the training time of extreme learning, according to an embodiment of the present invention, the feature is further included as a training sample,
and performing cluster analysis on the plurality of features, and taking the result of the cluster analysis as the training sample.
In the embodiment of the invention, after the clustering analysis is carried out on the plurality of features, the correlation among the features in each data cluster is higher, so that the features with higher correlation are selected as the training samples, the training time of extreme learning is reduced, and the training efficiency is improved.
According to an embodiment of the present invention, in order to improve the prediction accuracy of the trained network traffic prediction model, the network traffic prediction model may be further optimized. Specifically, traffic data including predetermined features are used as model verification samples, and the network traffic prediction model is optimized by using the model verification samples.
In the embodiment of the invention, the predetermined characteristics can comprise significant characteristics and non-significant characteristics, the network traffic data can be subjected to characteristic labeling by a manual empirical analysis method, the network traffic data comprising the predetermined significant characteristics and the non-significant characteristics is taken as a model verification sample, the prediction result of the model verification sample is calculated by using a network traffic prediction model, and then the network traffic prediction model is optimized according to the prediction result and the actual value of the model verification sample.
According to an embodiment of the present invention, as shown in fig. 3, the process of optimizing the network traffic prediction model using traffic data including predetermined characteristics as model verification samples further includes,
step 301: calculating the model verification sample by using the network traffic prediction model to obtain a prediction result corresponding to the model verification sample;
step 302: calculating the difference and variance of the prediction result and the actual value of the model verification sample;
step 303: and optimizing the network flow prediction model by taking the difference value and the variance as prediction error evaluation indexes and taking the minimum prediction error as a decision condition.
In the embodiment of the present invention, the prediction result obtained by calculating the model verification sample by the network traffic prediction model is the network traffic at the next time of the model verification sample, so that the model verification sample may be input into the network traffic prediction model according to the time sequence thereof, the prediction result corresponding to the sample at each time (i.e., the network traffic at the next time) is calculated respectively, then the calculated network traffic at the next time and the network traffic at the next time of the sample calculated this time in the model verification sample are taken as actual values, then the difference and the variance between the prediction result and the actual values are calculated, and the difference and the variance are taken as the prediction error evaluation index.
The difference and the variance are used as prediction evaluation indexes, so that quantitative evaluation of the prediction accuracy of the network flow model is realized, and the smaller the difference and the variance is, the higher the prediction accuracy of the network flow model is, and the better the prediction performance is.
Based on the same inventive concept, an embodiment of the present invention further provides a device for constructing a network traffic prediction model, as shown in fig. 4, including,
a historical network traffic data obtaining unit 401, configured to obtain historical network traffic data arranged in a time sequence;
a wavelet decomposition unit 402, configured to perform wavelet decomposition on the historical network traffic data to obtain a multi-scale component of the historical network traffic data;
a phase space reconstruction unit 403, configured to perform phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network traffic subsequence;
a feature extraction unit 404, configured to perform feature extraction on the historical network traffic data according to the nonlinear network traffic sub-sequence, and use the extracted multiple pieces of network traffic data as multiple features;
and a model training unit 405, configured to input the multiple features as training samples into an extreme learning model for training, so as to obtain a network traffic prediction model.
Because the principle of the device for solving the problems is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and repeated details are not repeated.
Based on the same inventive concept, an embodiment of the present invention further provides a method for predicting network traffic, as shown in fig. 5, including,
step 501: acquiring current network flow data;
step 502: the network traffic prediction model constructed according to the construction method of the network traffic prediction model of the embodiment of the invention calculates the current network traffic data to obtain the network traffic data after the current network traffic data, so as to evaluate the future network service quality according to the calculated network traffic data.
In the embodiment of the invention, the current network traffic data is calculated according to the network traffic prediction model to obtain the network traffic data at the time after the current network traffic data, so that the future network traffic is predicted, and the future network service quality is evaluated according to the calculated network traffic data.
Based on the same inventive concept, an embodiment of the present invention further provides a device for predicting network traffic, as shown in fig. 6, including,
a current network traffic data obtaining unit 601, configured to obtain current network traffic data;
the future network traffic data calculating unit 602 is configured to calculate the current network traffic data according to the network traffic prediction model constructed by the method for constructing a network traffic prediction model according to the embodiment of the present invention, so as to obtain network traffic data after the current network traffic data, so as to evaluate future network service quality according to the calculated network traffic data.
Fig. 7 is a schematic structural diagram of a computer device according to an embodiment of the present invention, where an apparatus in the present invention may be the computer device in the embodiment, and execute the method of the present invention. The computer device 702 may include one or more processing devices 704, such as one or more Central Processing Units (CPUs), each of which may implement one or more hardware threads. The computer device 702 may also include any storage resources 706 for storing any kind of information, such as code, settings, data, etc. For example, and without limitation, the storage resources 706 may include any one or more of the following in combination: any type of RAM, any type of ROM, flash memory devices, hard disks, optical disks, etc. More generally, any storage resource may use any technology to store information. Further, any storage resource may provide volatile or non-volatile reservation of information. Further, any storage resource may represent a fixed or removable component of computer device 702. In one case, when the processing device 704 executes associated instructions that are stored in any storage resource or combination of storage resources, the computer device 702 can perform any of the operations of the associated instructions. The computer device 702 also includes one or more drive mechanisms 708, such as a hard disk drive mechanism, an optical disk drive mechanism, or the like, for interacting with any storage resource.
An embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the above method.
Embodiments of the present invention further provide a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the computer program implements the foregoing method.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (11)
1. A method for constructing a network traffic prediction model, the method comprising,
acquiring historical network flow data arranged according to a time sequence;
performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data;
performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence;
extracting the characteristics of the historical network flow data according to the nonlinear network flow sub-sequence, and taking the extracted multiple network flow data as multiple characteristics;
and inputting the plurality of characteristics as training samples into an extreme learning model for training to obtain a network flow prediction model.
2. The method of claim 1, wherein performing feature extraction on the historical network traffic data based on the non-linear network traffic sub-sequence to obtain a plurality of features further comprises,
and according to the time sequence of the historical network flow data, data corresponding to the nonlinear network flow subsequences in the historical network flow data are taken from back to front to obtain the multiple features.
3. The method of claim 1, wherein using the features as training samples further comprises,
and performing cluster analysis on the plurality of features, and taking the result of the cluster analysis as the training sample.
4. The method of claim 1, wherein after obtaining the network traffic prediction model, the method further comprises,
and optimizing the network traffic prediction model by taking the traffic data comprising the preset characteristics as a model verification sample.
5. The method of claim 4, wherein traffic data comprising predetermined characteristics is used as model validation samples, and optimizing the network traffic prediction model further comprises,
calculating the model verification sample by using the network traffic prediction model to obtain a prediction result corresponding to the model verification sample;
calculating the difference and variance of the prediction result and the actual value of the model verification sample;
and optimizing the network flow prediction model by taking the minimum prediction error as a decision condition by taking the difference and the variance as prediction error evaluation indexes.
6. A device for constructing a network traffic prediction model is characterized by comprising,
the historical network flow data acquisition unit is used for acquiring historical network flow data arranged according to a time sequence;
the wavelet decomposition unit is used for performing wavelet decomposition on the historical network traffic data to obtain multi-scale components of the historical network traffic data;
the phase space reconstruction unit is used for performing phase space reconstruction on the decomposed multi-scale components to obtain a nonlinear network flow subsequence;
the characteristic extraction unit is used for extracting the characteristics of the historical network traffic data according to the nonlinear network traffic subsequence, and taking the extracted multiple network traffic data as multiple characteristics;
and the model training unit is used for inputting the plurality of characteristics as training samples into the extreme learning model for training to obtain the network flow prediction model.
7. A method for predicting network traffic, comprising,
acquiring current network flow data;
the network traffic prediction model constructed according to the method for constructing a network traffic prediction model according to any one of claims 1 to 5 calculates the current network traffic data to obtain the network traffic data after the current network traffic data, so as to evaluate the future network service quality according to the calculated network traffic data.
8. An apparatus for predicting network traffic, comprising:
a current network traffic data obtaining unit, configured to obtain current network traffic data;
a future network traffic data calculating unit, configured to calculate the current network traffic data according to the network traffic prediction model constructed by the method for constructing a network traffic prediction model according to any one of claims 1 to 5, to obtain network traffic data after the current network traffic data, so as to evaluate future network service quality according to the calculated network traffic data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 5 or 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method of any one of claims 1 to 5 or 7.
11. A computer program product, characterized in that the computer program product comprises a computer program which, when executed by a processor, implements the method of any one of claims 1 to 5 or claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210883364.3A CN115022210B (en) | 2022-07-26 | 2022-07-26 | Construction method, prediction method and device of network traffic prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210883364.3A CN115022210B (en) | 2022-07-26 | 2022-07-26 | Construction method, prediction method and device of network traffic prediction model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115022210A true CN115022210A (en) | 2022-09-06 |
| CN115022210B CN115022210B (en) | 2024-06-21 |
Family
ID=83080598
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210883364.3A Active CN115022210B (en) | 2022-07-26 | 2022-07-26 | Construction method, prediction method and device of network traffic prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115022210B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117041073A (en) * | 2023-09-05 | 2023-11-10 | 广州天懋信息系统股份有限公司 | Network behavior prediction method, system, equipment and storage medium |
| CN117201334A (en) * | 2023-11-08 | 2023-12-08 | 之江实验室 | Multi-mode network traffic prediction method and device |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101729315A (en) * | 2009-12-24 | 2010-06-09 | 北京邮电大学 | Network flow-predicting method and device based on wavelet package decomposition and fuzzy neural network |
| CN110677297A (en) * | 2019-09-29 | 2020-01-10 | 北京工业大学 | Combined network flow prediction method based on autoregressive moving average model and extreme learning machine |
| CN110858805A (en) * | 2018-08-23 | 2020-03-03 | 中国移动通信集团山东有限公司 | Method and device for predicting network traffic of cell |
| CN111397901A (en) * | 2019-03-12 | 2020-07-10 | 上海电机学院 | Rolling bearing fault diagnosis method based on wavelet and improved PSO-RBF neural network |
| CN112241599A (en) * | 2020-11-18 | 2021-01-19 | 中国联合网络通信集团有限公司 | Method and device for establishing fault analysis model |
| CN113037577A (en) * | 2019-12-09 | 2021-06-25 | 中国电信股份有限公司 | Network traffic prediction method, device and computer readable storage medium |
| CN114244594A (en) * | 2021-12-10 | 2022-03-25 | 天元大数据信用管理有限公司 | Network flow abnormity detection method and detection system |
-
2022
- 2022-07-26 CN CN202210883364.3A patent/CN115022210B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101729315A (en) * | 2009-12-24 | 2010-06-09 | 北京邮电大学 | Network flow-predicting method and device based on wavelet package decomposition and fuzzy neural network |
| CN110858805A (en) * | 2018-08-23 | 2020-03-03 | 中国移动通信集团山东有限公司 | Method and device for predicting network traffic of cell |
| CN111397901A (en) * | 2019-03-12 | 2020-07-10 | 上海电机学院 | Rolling bearing fault diagnosis method based on wavelet and improved PSO-RBF neural network |
| CN110677297A (en) * | 2019-09-29 | 2020-01-10 | 北京工业大学 | Combined network flow prediction method based on autoregressive moving average model and extreme learning machine |
| CN113037577A (en) * | 2019-12-09 | 2021-06-25 | 中国电信股份有限公司 | Network traffic prediction method, device and computer readable storage medium |
| CN112241599A (en) * | 2020-11-18 | 2021-01-19 | 中国联合网络通信集团有限公司 | Method and device for establishing fault analysis model |
| CN114244594A (en) * | 2021-12-10 | 2022-03-25 | 天元大数据信用管理有限公司 | Network flow abnormity detection method and detection system |
Non-Patent Citations (2)
| Title |
|---|
| 卢振利;: "相空间重构和正则极限学习机的网络流量预测", 激光杂志, no. 01 * |
| 胡竟伟;: "基于WA-ELM的网络流量混沌预测模型", 微电子学与计算机, no. 06, pages 2 - 5 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117041073A (en) * | 2023-09-05 | 2023-11-10 | 广州天懋信息系统股份有限公司 | Network behavior prediction method, system, equipment and storage medium |
| CN117041073B (en) * | 2023-09-05 | 2024-05-28 | 广州天懋信息系统股份有限公司 | Network behavior prediction method, system, equipment and storage medium |
| CN117201334A (en) * | 2023-11-08 | 2023-12-08 | 之江实验室 | Multi-mode network traffic prediction method and device |
| CN117201334B (en) * | 2023-11-08 | 2024-01-26 | 之江实验室 | Multi-mode network traffic prediction method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115022210B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115022210B (en) | Construction method, prediction method and device of network traffic prediction model | |
| JP7343568B2 (en) | Identifying and applying hyperparameters for machine learning | |
| WO2021084286A1 (en) | Root cause analysis in multivariate unsupervised anomaly detection | |
| CN107273979B (en) | Method and system for performing machine learning prediction based on service level | |
| CN113869521A (en) | Method, device, computing equipment and storage medium for constructing prediction model | |
| CN110825522A (en) | Spark parameter self-adaptive optimization method and system | |
| CN111582341A (en) | User abnormal operation prediction method and device | |
| CN111935140A (en) | Abnormal message identification method and device | |
| AU2021285952B2 (en) | Streamlining data processing optimizations for machine learning workloads | |
| CN112396166A (en) | Graph convolution neural network training method and device based on mixed granularity aggregator | |
| CN116956994A (en) | Service platform capacity expansion prediction method and device | |
| Subramaniam et al. | Improving process models by discovering decision points | |
| JP7306432B2 (en) | Information processing method, information processing device and program | |
| CN114155410A (en) | Graph pooling, classification model training and reconstruction model training method and device | |
| US10394810B1 (en) | Iterative Z-score calculation for big data using components | |
| CN113435113B (en) | Power system transient stability evaluation method and device | |
| CN112750047A (en) | Behavior relation information extraction method and device, storage medium and electronic equipment | |
| Nguyen et al. | Jointly optimize coding and node selection for distributed computing over wireless edge networks | |
| CN113591458B (en) | Medical term processing method, device, equipment and storage medium based on neural network | |
| CN113220547B (en) | Complex software system reliability index determining method based on simulation | |
| CN114615144B (en) | Network optimization method and system | |
| CN115545186A (en) | Model optimization method, device, equipment and storage medium | |
| CN117077809A (en) | Abnormal data analysis method and system based on wind control decision and visualization | |
| CN116307218A (en) | Meta-universe experience user behavior prediction method and system based on artificial intelligence | |
| CN114022274A (en) | Graph neural network structure searching method and system |
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 |