CN113850282A - Traffic management method, system and device based on dynamic classification - Google Patents
Traffic management method, system and device based on dynamic classification Download PDFInfo
- Publication number
- CN113850282A CN113850282A CN202110599791.4A CN202110599791A CN113850282A CN 113850282 A CN113850282 A CN 113850282A CN 202110599791 A CN202110599791 A CN 202110599791A CN 113850282 A CN113850282 A CN 113850282A
- Authority
- CN
- China
- Prior art keywords
- type
- traffic
- flow
- network traffic
- network
- 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
- 238000007726 management method Methods 0.000 title claims abstract description 20
- 238000013145 classification model Methods 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 20
- 230000008859 change Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 12
- 238000002360 preparation method Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 238000012216 screening Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 25
- 238000012546 transfer Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 4
- 239000012634 fragment Substances 0.000 claims description 3
- 238000007635 classification algorithm Methods 0.000 claims description 2
- 238000000354 decomposition reaction Methods 0.000 claims description 2
- 206010003694 Atrophy Diseases 0.000 claims 1
- 230000037444 atrophy Effects 0.000 claims 1
- 238000012512 characterization method Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a flow management method, a system and a device based on dynamic classification. A data preparation module collects network flow screening characteristic data and prints a type label according to an application type; constructing a network traffic classification model by an online training module through an XGboost algorithm; based on the model, the traffic classification module classifies the network traffic; the traffic type trend analysis module statistically analyzes the change trend state of each type of classified network traffic within a period of time to classify each type of network traffic into trend state types; the PHB mapping module maps different types of network traffic to different PHB types; and the flow distribution module is used for forwarding the network flow in real time according to self-carried forwarding strategies of different PHB types. The invention combines the network traffic type and the traffic management method of dynamic and rapid classification of the change trend of each type of traffic, meets the real-time requirement and improves the user experience.
Description
Technical Field
The invention relates to the field of internet, in particular to a method, a system and a device for network traffic management based on dynamic classification.
Background
With the continuous development of internet technology, the number of various applications is increased dramatically, and especially with the rise of applications such as short videos, cloud disks, cloud games and the like, users enter a period of explosive growth for network traffic demands, and higher requirements are put forward for network quality.
According to the annual report of the quality of the China network in 2020 issued by Internet data center IDC, 45% of China netizens represent that the network is poor in experience, wherein the first ranking factor is network Caton.
An operator facing the problem firstly considers that a plurality of network applications have own network characteristics, the respective network applications have different real-time requirements, and the traditional one-view-same-kernel forwarding mode cannot meet the higher real-time requirement of part of the applications but appears to be waste for the other part of the applications, so that the method is a feasible coping method for taking measures to perform differentiated classification management on network traffic and preferentially meeting the application with high real-time requirement on the premise of small overall bandwidth change. Specifically, based on the classification of network traffic, an appropriate transmission environment is customized for different applications (traffic types), thereby improving the access perception of network applications and improving customer satisfaction.
The traditional traffic classification method comprises TCP port identification and deep packet inspection DPI, and the traditional traffic classification method is essentially to analyze network traffic data packets to obtain contained effective data and then to achieve classification by matching certain characteristic fields.
The network traffic classification technology based on TCP port identification classifies according to the TCP protocol and the method has simple algorithm, but the accuracy is continuously reduced and the application range is greatly reduced along with the occurrence of port hopping and port disguising technology.
The network traffic classification technology based on Deep Packet Inspection (DPI) is a technology for classifying network traffic by analyzing effective data of a network traffic data packet and matching the effective data with a known program or protocol, but the technology is influenced by data encryption and privacy problems, and a classification result cannot meet commercial conditions.
In addition, no matter based on the TCP port identification technology or the deep packet inspection DPI technology, the classification of the TCP port identification technology and the deep packet inspection DPI technology is to classify the network traffic according to the artificially set static rules, which does not meet the real-time intelligent requirement.
For example, CN112187653A discloses a method for determining network traffic, which includes obtaining a traffic, determining a traffic pattern corresponding to the traffic, invoking a traffic classification model based on the traffic pattern, and determining a traffic type of the traffic based on the traffic classification model. The method is static classification, does not establish a dynamic classification recognition model aiming at a complex network scene, and has no industrial universality.
For another example, the network traffic determination method disclosed in CN112187652A collects multiple sample traffic within a period of time, clusters the multiple sample traffic to obtain multiple sample traffic types, and establishes an initial feature extraction rule and an initial feature determination rule based on the multiple sample traffic types. The method establishes a flow judgment rule based on the clustering samples in specific time, does not consider the multidimensional time sequence characteristics of the flow, and is easy to cause large error of a classification result.
Therefore, a traffic management method combining network traffic types and the variation trend of each type of traffic for dynamic and rapid classification is needed to meet the real-time requirement and improve the user experience.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter; nor is it intended to be used as an aid in determining or limiting the scope of the claimed subject matter.
The invention provides a dynamic network traffic classification method, system and device based on machine learning. The method comprises the steps of establishing an effective characteristic database for flow classification by collecting network flow characteristic data, then utilizing an extreme gradient lifting XGboost algorithm to establish a network flow classification model on line, outputting a network flow classification result according to the network flow classification model, further mapping the classification result to different hop-by-hop behavior PHB types according to the real-time requirement and the variation trend of each type of flow type, matching a differentiated flow management strategy, and forwarding the network flow in real time through self-carried forwarding strategies of different PHB types. Therefore, the follow-up service can meet respective real-time requirements, and the use experience of the client is improved. The classification effect and accuracy are higher than those of the existing TCP classification technology and DPI classification technology.
The traffic management system based on dynamic classification of the invention comprises: the system comprises a data preparation module, an online training module, a traffic classification module, a traffic type trend analysis module, a PHB mapping module and a traffic distribution module, wherein the data preparation module is used for collecting network traffic screening characteristic data and marking a type label according to an application type, the online training module is used for constructing a network traffic classification model through an XGboost algorithm based on network traffic marked with the type label, the traffic classification module is used for classifying the network traffic by using the network traffic classification model, the traffic type trend analysis module is used for statistically analyzing the change trend state of each type of classified network traffic within a period of time and dividing each type of network traffic into trend state types, the PHB mapping module is used for mapping different types of network traffic to different PHB type PHB mapping modules in combination with the network traffic type and the change trend state type, and the traffic distribution module is used for forwarding the network traffic in real time according to own forwarding strategies of different PHB types.
The traffic management method based on dynamic classification comprises the following steps: collecting flow data, extracting characteristic data, and marking a type label according to the type of application; performing online training by using the XGboost algorithm and utilizing the traffic data which is collected within a period of time and is printed with the type label to obtain a traffic classification model; classifying each of the collected flows using the flow classification model; constructing a characteristic project, and identifying the change trend state of each type of flow; mapping each type of traffic to a different PHB type; and forwarding according to the strategy corresponding to the PHB type of the real-time flow.
These and other features and advantages will become apparent upon reading the following detailed description and upon reference to the accompanying drawings. It is to be understood that both the foregoing general description and the following detailed description are explanatory only and are not restrictive of aspects as claimed.
Drawings
The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which specific embodiments of the invention are shown.
FIG. 1 is a block diagram of a dynamic network traffic management system of the present invention;
FIG. 2 is an overall flow diagram of the dynamic network traffic management method of the present invention;
FIG. 3 is a detailed flowchart of step S5 of the method of FIG. 2;
fig. 4 is a flow chart of traffic classification and forwarding of Chat class and Stream class according to a specific embodiment of the dynamic network traffic management method of the present invention.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
Detailed Description
The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which specific embodiments of the invention are shown. Various advantages and benefits of the present invention will become apparent to those of ordinary skill in the art upon reading the following detailed description of the specific embodiments. It should be understood, however, that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. The following embodiments are provided so that the invention may be more fully understood. Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by those of skill in the art to which this application belongs.
The invention provides a flow management method and system based on dynamic classification. By counting the characteristic data (the number of data packets, the number of bytes of the data packets, the field value of a fragment flag and the like) of network flow passing through a recent network node, dividing the network flow into 9 types according to the type of an application program, dividing each type of flow into a collapse type, a stable type and an increase type by counting the recent change trend state of each type of flow, mapping different types of network flow into PHB types in QoS (quality of service) by combining the requirement of the flow type on the real-time property of the network and the change trend of the flow type, generating a mapping strategy, and forwarding the real-time network flow after classifying according to the mapping strategy, thereby ensuring the requirement of different types of flow on the real-time property of the network and ensuring that the high-frequency flow can be forwarded at higher priority.
As shown in fig. 1, the traffic management system based on dynamic classification of the present invention includes: the system comprises a data preparation module, an online training module, a flow classification module, a flow type trend analysis module, a PHB mapping module and a flow distribution module. The method comprises the following specific steps:
a data preparation module: collecting network traffic at an observation point (such as a router or a three-layer switch) in a network within a period of time (such as one month, three months, half a year and the like), screening different traffic characteristic data which play a positive role in traffic classification for classification, performing statistical analysis, and marking type labels according to the applied types to obtain a data set marked with the type labels; in addition, the data preparation module is also responsible for collecting network flow data in real time;
an online training module: training a network traffic data set which is obtained by analyzing network traffic characteristic data collected within a period of time and is marked with a type label by a data preparation module, and constructing a network traffic classification model by an XGboost algorithm;
a traffic classification module: classifying the network traffic by using a network traffic classification model obtained by training of an online training module according to different feature data which are obtained by screening of a data preparation module and play a positive role in classifying the network traffic to obtain classified network traffic;
traffic type trend analysis module: dividing each type of network traffic into state types, for example, including a collapsing type traffic, a steady type traffic and an increasing type traffic, by statistically analyzing the change trend state of each type of network traffic within a period of time;
PHB mapping Module: mapping different traffic types to different PHB types by combining the network traffic type obtained by the analysis traffic classification module and the change trend state of each type obtained by the traffic type trend analysis module;
traffic forwarding module: and forwarding the network flow in real time according to self-carried forwarding strategies of different PHB types.
As shown in fig. 2, the traffic management method based on dynamic classification of the present invention includes:
in step S1, collecting network traffic for a period of time at an observation point (router or triple-layer switch) in the network, and extracting characteristic data therein, including the number of packets and the packet length of the packets; a source IP, a target IP, a Service Type of Service field value and a fragment tag Flags field value of the IP header; a source port, a destination port, a Data Offset field value of a header length, and an urgent flag URG field value of a TCP header; source port of UDP header, destination port, and duration of the entire network flow, etc.
The debugger classifies the network traffic characteristic data into categories according to application types and marks type labels, and the specific categories can be classified into the following nine categories, for example: chat (instant messaging application type), DNS (domain name system service application type), Email (Email application type), File transfer (File transfer application type), Game (multiplayer online Game application type), HTTP (hypertext transfer protocol application type), P2P (P2P File sharing application type), Stream (streaming media application type), and VoIP (voice over IP application type). Each type of traffic has different requirements on real-time and will be given different weights in subsequent steps.
In step S2, splitting the network traffic characteristic data acquired in step S1 into a training set and a test set, and selecting an XGBoost algorithm to complete training and testing work; and taking the network traffic characteristic data in the data set as nodes of tree splitting, and obtaining different scores after different types of network traffic generate trees, thereby obtaining a traffic classification model.
In step S3, each network traffic is classified according to the real-time feature data of each network traffic obtained in step S1 and the classification model trained in step S2, so as to obtain the type of each network traffic. After t decision trees are trained, each network traffic is classified and predicted to be:
wherein,representing the output network traffic classification prediction score, t representing the number of decision trees, fkRepresenting a particular tree, xiRepresenting incoming network traffic, predicting scores by classificationThe current traffic type is judged according to the size of the traffic.
At step S4: constructing a feature project for the network data collected in step S1: the characteristics of the total amount of each type of flow are counted, such as: statistical characteristics such as mean value, maximum value, median, minimum value and the like of the granularity at the time of nearly 7 days, 1 month, 6 months and the like; decomposing the trend items of each index by using a time sequence decomposition algorithm, and judging the change trend of the index; and according to the output of the characteristic engineering, constructing a flow type trend state classification model by using an SVM classification algorithm, thereby identifying whether the trend state of each flow type is atrophic, steady or increased.
In step S5, the different types of traffic classes are mapped to different PHB types according to the different types of traffic obtained in step S3 and the trend of change of the corresponding types of traffic obtained in step S4, where the PHB types include a DF (default forwarding) type and four levels of AF (assured forwarding) types including AF1, AF2, AF3, AF4, and EF (expedited forwarding) types.
In step S6, the real-time network traffic is forwarded according to the type of the real-time network traffic obtained in step S3 and the PHB type corresponding to each traffic type obtained in step S5, so as to improve the network service quality.
The following discusses, in conjunction with fig. 3, the specific step of mapping the different types of traffic classes to the different PHB types in step S5 in fig. 2:
step S5-1: adding initial weight values w (i) to the different types of network traffic in step S1 according to the requirement for real-time performance, for example, setting the initial weight values of HTTP type, P2P type, Email type, File transfer type, DNS type, Chat type, Game type, Stream type, and VoIP type to 1, 2, 3, 4, 5, and 6, respectively;
step S5-2: adding additional weight values a (i) to the traffic types of different trend states obtained in step S4, for example, setting the additional weight values of the traffic types of the collapse type, the steady type and the growth type to 1, 2 and 3, respectively;
step S5-3: adding the initial weight value w (i) in step S5-1 and the additional weight value a (i) in step S5-2 to obtain the final weight values of different types of traffic, for example, the possible outcomes are 2, 3, 4, 5, 6, 7, 8 and 9;
step S5-4: and marking the different types of traffic classes as EF, AF4, AF3, AF2, AF1 and DF types in the PHB according to the final weight values obtained in the step S5-3, wherein the traffic types with the final weight values of 2 and 3 are marked as DF type default forwarding, the traffic types with the final weight values of 4, 5, 6 and 7 are respectively marked as AF1, AF2, AF3 and AF4 types to ensure forwarding, and the traffic types with the weight values of 8 and 9 are marked as EF types to be forwarded quickly.
Fig. 4 is a flow chart of traffic classification and forwarding tagged with a Chat class and a Stream class at step S1 according to an embodiment of the present invention. The method comprises the following specific steps:
step S100: adding an initial weight value to the network real-time requirement by analyzing different types of traffic, wherein W (Chat) is 4, and W (Stream) is 5;
step S200: adding an additional weight value for the flow rate through the change trend of the two types of flow rates, wherein the flow rate of the Chat type is in an increasing type, the flow rate of the Stream type is in a collapsing type, and the additional weight value is added for the flow rate of the Stream type, wherein A (Chat) is 3, and A (Stream) is 1;
step S300: combining the initial weight value and the additional weight value to obtain a final weight value of 7 for the Chat type flow, a final weight value of 6 for the streamline type flow, and generating PHB mapping strategies with corresponding PHB types of AF4 and AF3 respectively;
step S400: and collecting real-time network traffic and analyzing the type of the real-time network traffic, forwarding according to AF4 if the traffic is Chat type traffic, forwarding according to AF3 if the traffic is streamline type traffic, wherein the AF4 has higher priority than AF 3.
The traffic management method and system based on dynamic classification establish a set of characteristic data models in a complex network scene, sufficiently combine recent trend change characteristics of traffic, endow different weights, generate a differential management strategy and meet the diversified requirements of identification of general traffic. The method is suitable for traffic identification and traffic scheduling in large and medium Internet environments (such as operator networks, large IDC networks and the like), and has wide applicability. The method and the system of the invention fully utilize the bandwidth resources of the internet, improve the network reuse rate, effectively improve the response speed of the large and medium-sized internet and effectively solve the difficult problems of classification and scheduling of the large and medium-sized network.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present disclosure, and the present disclosure should be construed as being covered by the claims and the specification.
Claims (10)
1. A traffic management method based on dynamic classification comprises the following steps:
collecting flow data, extracting characteristic data, and marking a type label according to the type of application;
performing online training by using the XGboost algorithm and utilizing the traffic data which is collected within a period of time and is printed with the type label to obtain a traffic classification model;
classifying each of the collected flows using the flow classification model;
constructing a characteristic project, and identifying the change trend state of each type of flow;
mapping each type of traffic to a different PHB type; and
and forwarding according to the strategy corresponding to the PHB type of the real-time flow.
2. The method of claim 1, wherein mapping each type of traffic to a different PHB type further comprises:
adding an initial weight value to each type of flow according to the real-time requirement;
adding an additional weight value to each type of flow according to different change trend states;
adding the initial weight value and the additional weight value to obtain a final weight value; and
and mapping each type of flow to different PHB types according to the final weight value.
3. The method of claim 1, wherein the characterization data comprises one or more of: the number of data packets and the packet length of the data packets; a source IP, a target IP, a Service Type of Service field value and a fragment tag Flags field value of the IP header; a source port, a destination port, a Data Offset field value of a header length, and an urgent flag URG field value of a TCP header; source port, destination port, and duration of the entire network flow for the UDP header.
4. The method of claim 1, wherein tagging a type according to a type of application comprises: an instant messaging application type, a domain name system service application type, an email application type, a file transfer application type, a multiplayer online game application type, a hypertext transfer protocol application type, a P2P file sharing application type, a streaming media application type, and an IP telephony application type.
5. The method of claim 1, wherein the step of obtaining a traffic classification model comprises: and splitting the data obtained in the preamble step into a training set and a testing set, selecting an XGboost algorithm to perform training and testing work, taking the characteristic data as nodes of tree splitting, and obtaining different scores after different types of network traffic generate trees, thereby obtaining a traffic classification model.
6. The method of claim 5, wherein each real-time network traffic classification prediction score is:
7. The method of claim 1, wherein identifying a trend state for each type of flow comprises:
counting the characteristics of the average value, the maximum value, the median and the minimum value of the total flow of each type according to the time granularity;
decomposing the trend item of the characteristic index by using a time sequence decomposition algorithm, and judging the change trend of the index;
constructing a flow type trend state classification model by utilizing an SVM classification algorithm; and
identifying whether the trend state for each flow type is atrophic, stationary, or growing.
8. The method of claim 1, wherein the PHB types comprise DF default forwarding, EF expedited forwarding, and AF assured forwarding, wherein the AFs further comprise different weights of AF1, AF2, AF3, and AF 4.
9. A dynamic classification-based traffic management system, comprising:
the data preparation module is used for acquiring network flow, screening characteristic data and marking a type label according to an application type;
the online training module is used for constructing a network traffic classification model through an XGboost algorithm based on the network traffic marked with the type label;
the traffic classification module is used for classifying the network traffic by utilizing the network traffic classification model;
the traffic type trend analysis module is used for statistically analyzing the change trend state of each type of classified network traffic within a period of time so as to divide each type of network traffic into trend state types;
the PHB mapping module is used for mapping different types of network traffic to different PHB types by combining the network traffic type and the change trend state type; and
and the flow distribution module is used for forwarding the network flow in real time according to self-carried forwarding strategies of different PHB types.
10. The system of claim 9, wherein:
the type label printed according to the application type comprises: an instant messaging application type, a domain name system service application type, an email application type, a file transfer application type, a multiplayer online game application type, a hypertext transfer protocol application type, a P2P file sharing application type, a streaming media application type, and an IP telephony application type;
the trend status types include atrophy, plateau, and growth; and
the PHB type comprises DF default forwarding, EF quick forwarding and AF guarantee forwarding.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599791.4A CN113850282A (en) | 2021-05-31 | 2021-05-31 | Traffic management method, system and device based on dynamic classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110599791.4A CN113850282A (en) | 2021-05-31 | 2021-05-31 | Traffic management method, system and device based on dynamic classification |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113850282A true CN113850282A (en) | 2021-12-28 |
Family
ID=78973020
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110599791.4A Pending CN113850282A (en) | 2021-05-31 | 2021-05-31 | Traffic management method, system and device based on dynamic classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113850282A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118101999A (en) * | 2024-04-29 | 2024-05-28 | 天津北方盛世科技有限公司 | Short video flow data analysis method |
WO2024125183A1 (en) * | 2022-12-12 | 2024-06-20 | 中兴通讯股份有限公司 | Traffic identification method, terminal device, and storage medium |
-
2021
- 2021-05-31 CN CN202110599791.4A patent/CN113850282A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2024125183A1 (en) * | 2022-12-12 | 2024-06-20 | 中兴通讯股份有限公司 | Traffic identification method, terminal device, and storage medium |
CN118101999A (en) * | 2024-04-29 | 2024-05-28 | 天津北方盛世科技有限公司 | Short video flow data analysis method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | Network traffic classification using k-means clustering | |
CN109831386B (en) | Optimal path selection algorithm based on machine learning under SDN | |
Alshammari et al. | A flow based approach for SSH traffic detection | |
CN110311829A (en) | A kind of net flow assorted method accelerated based on machine learning | |
CN113158390B (en) | Network attack traffic generation method for generating countermeasure network based on auxiliary classification | |
CN100553206C (en) | Internet, applications method for recognizing flux based on packet sampling and application signature | |
CN113850282A (en) | Traffic management method, system and device based on dynamic classification | |
CN109167680A (en) | A kind of traffic classification method based on deep learning | |
CN107819646A (en) | A kind of net flow assorted system and method for distributed transmission | |
CN109151880A (en) | Mobile application flow identification method based on multilayer classifier | |
Aureli et al. | Going beyond diffserv in ip traffic classification | |
CN110324327A (en) | User and server ip address caliberating device and method based on specific enterprise domain name data | |
CN114553722B (en) | VPN and non-VPN network flow classification method based on multi-view one-dimensional convolutional neural network | |
CN112884121A (en) | Traffic identification method based on generation of confrontation deep convolutional network | |
Chen et al. | Online hybrid traffic classifier for Peer-to-Peer systems based on network processors | |
CN116684877A (en) | GYAC-LSTM-based 5G network traffic anomaly detection method and system | |
CN101764754B (en) | Sample acquiring method in business identifying system based on DPI and DFI | |
CN114650229A (en) | Network encryption traffic classification method and system based on three-layer model SFTF-L | |
CN114598499A (en) | Network risk behavior analysis method combined with business application | |
CN112839051A (en) | Encryption flow real-time classification method and device based on convolutional neural network | |
CN115242724B (en) | High-speed network traffic service classification method based on two-stage clustering | |
Deebalakshmi et al. | A survey of classification algorithms for network traffic | |
Tang et al. | Intelligent awareness of delay-sensitive internet traffic in digital twin network | |
CN114124565A (en) | Network intrusion detection method based on graph embedding | |
CN110175635B (en) | OTT application program user classification method based on Bagging algorithm |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20220128 Address after: Room 1423, No. 1256 and 1258, Wanrong Road, Jing'an District, Shanghai 200072 Applicant after: Tianyi Digital Life Technology Co.,Ltd. Address before: 201702 3rd floor, 158 Shuanglian Road, Qingpu District, Shanghai Applicant before: Tianyi Smart Family Technology Co.,Ltd. |