CN102857474A - Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology - Google Patents
Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology Download PDFInfo
- Publication number
- CN102857474A CN102857474A CN2011101783823A CN201110178382A CN102857474A CN 102857474 A CN102857474 A CN 102857474A CN 2011101783823 A CN2011101783823 A CN 2011101783823A CN 201110178382 A CN201110178382 A CN 201110178382A CN 102857474 A CN102857474 A CN 102857474A
- Authority
- CN
- China
- Prior art keywords
- svm
- traffic
- flow
- peer
- technology
- 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
Images
Abstract
The invention discloses a method for identifying and classifying P2P (peer-to-peer) traffic on the basis of an SVM (support vector machine) technology, and relates to identification and classification of P2P traffic. The method includes steps of creating a P2P traffic identifying model on the basis of a two-dimensional SVM mechanism; improving an SVM algorithm; analyzing statistic characteristics of the P2P traffic; and identifying and classifying the P2P traffic on the basis of the statistic characteristics of the traffic and the improved SVM mechanism. By the method, the SVM technology is improved, and the P2P traffic can be effectively identified and classified.
Description
Technical field
The present invention relates to identification and the sorting technique of P2P flow, relate in particular to a kind of identification of P2P flow and sorting technique based on the SVM technology.
Background technology
Along with the development of network, P2P network technology of new generation is widely used.The P2P of current popular uses and mainly comprises file-sharing, P2P streaming media video and instant messaging etc.In the time of P2P technology development, various P2P use the network traffic data that produces and have surpassed traditional Network, HTTP and FTP account for more than 80% of whole Internet flow, become the maximum consumer of the network bandwidth, bring white elephant to network, brought huge challenge also for each the large management P2P of operator flow.The Internet massive band width is used by P2P and is occupied, service quality to other application has formed threat, has also damaged Internet Service Provider's interests, for the operation that guarantees that network is can be normally orderly, be necessary the P2P network traffics are carried out control and management, improve the performance of network service.Net flow assorted is understanding, management, optimize the important evidence of various network resources, and Qos management, trend analysis and the safety detection of network had very important effect.In this simultaneously, adopt dynamic ports, agreement encryption, Data Encryption Transmission and otherwise reason owing to many new P2P are professional so that traditional based on port traffic classification and based on the sorting technique that the deep layer packet the detects P2P network traffics of can not effectively having identified and classify.
Summary of the invention
A kind of identification of P2P flow and the sorting technique based on the SVM technology of the present invention's invention may further comprise the steps:
Foundation is based on the P2P flow model of cognition step of two-dimentional SVM mechanism, analyzes the SVM algorithm, and according to the P2P flow model of cognition of setting up based on the statistical property vector of the abnormal traffic detection model of SVM and P2P flow based on two-dimentional SVM mechanism;
To the improvement step of SVM algorithm, utilize the multidimensional SVM mechanism that the mode of vectorial weighting is realized finishing the P2P traffic classification, and set up P2P traffic classification based on this improved SVM mechanism near model;
The analytical procedure of P2P traffic statistics characteristic is according to the setting of the Analysis deterrmination of P2P traffic statistics characteristic vector weight and the automatic adjustment of weights;
P2P flow recognition and classification step based on traffic statistics characteristic and improvement SVM.
A kind of identification of P2P flow and sorting technique based on the SVM technology of the present invention's invention is optimized the SVM technology, can effectively the P2P flow be identified and classify.
Description of drawings
Fig. 1 be the present invention invent a kind of based on the SVM technology the identification of P2P flow and the flow chart of steps of sorting technique.
Embodiment
The present invention invention a kind of based on the SVM technology the identification of P2P flow and the flow chart of steps of sorting technique as shown in Figure 1, comprise following steps:
Foundation is based on the P2P flow model of cognition step of two-dimentional SVM mechanism, analyzes the SVM algorithm, and according to the P2P flow model of cognition of setting up based on the statistical property vector of the abnormal traffic detection model of SVM and P2P flow based on two-dimentional SVM mechanism;
To the improvement step of SVM algorithm, utilize the multidimensional SVM mechanism that the mode of vectorial weighting is realized finishing the P2P traffic classification, and set up P2P traffic classification based on this improved SVM mechanism near model;
The analytical procedure of P2P traffic statistics characteristic is according to the setting of the Analysis deterrmination of P2P traffic statistics characteristic vector weight and the automatic adjustment of weights;
P2P flow recognition and classification step based on traffic statistics characteristic and improvement SVM.
Claims (1)
1. the identification of P2P flow and sorting technique based on a SVM technology is characterized in that, may further comprise the steps:
Foundation is based on the P2P flow model of cognition step of two-dimentional SVM mechanism, analyzes the SVM algorithm, and according to the P2P flow model of cognition of setting up based on the statistical property vector of the abnormal traffic detection model of SVM and P2P flow based on two-dimentional SVM mechanism;
To the improvement step of SVM algorithm, utilize the multidimensional SVM mechanism that the mode of vectorial weighting is realized finishing the P2P traffic classification, and set up P2P traffic classification based on this improved SVM mechanism near model;
The analytical procedure of P2P traffic statistics characteristic is according to the setting of the Analysis deterrmination of P2P traffic statistics characteristic vector weight and the automatic adjustment of weights;
P2P flow recognition and classification step based on traffic statistics characteristic and improvement SVM.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101783823A CN102857474A (en) | 2011-06-29 | 2011-06-29 | Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101783823A CN102857474A (en) | 2011-06-29 | 2011-06-29 | Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102857474A true CN102857474A (en) | 2013-01-02 |
Family
ID=47403674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011101783823A Pending CN102857474A (en) | 2011-06-29 | 2011-06-29 | Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102857474A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021114844A1 (en) * | 2019-12-10 | 2021-06-17 | 华为技术有限公司 | Traffic classification method and traffic management device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345704A (en) * | 2008-08-15 | 2009-01-14 | 南京邮电大学 | Equity network flux detection method based on supporting vector machine |
| CN101447995A (en) * | 2008-12-30 | 2009-06-03 | 成都市华为赛门铁克科技有限公司 | Method for identifying P2P data stream, device and system thereof |
| CN101510873A (en) * | 2009-03-20 | 2009-08-19 | 扬州永信计算机有限公司 | Method for detection of mixed point-to-point flux based on vector machine support |
| CN101795214A (en) * | 2010-01-22 | 2010-08-04 | 华中科技大学 | Behavior-based P2P detection method under large traffic environment |
-
2011
- 2011-06-29 CN CN2011101783823A patent/CN102857474A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101345704A (en) * | 2008-08-15 | 2009-01-14 | 南京邮电大学 | Equity network flux detection method based on supporting vector machine |
| CN101447995A (en) * | 2008-12-30 | 2009-06-03 | 成都市华为赛门铁克科技有限公司 | Method for identifying P2P data stream, device and system thereof |
| CN101510873A (en) * | 2009-03-20 | 2009-08-19 | 扬州永信计算机有限公司 | Method for detection of mixed point-to-point flux based on vector machine support |
| CN101795214A (en) * | 2010-01-22 | 2010-08-04 | 华中科技大学 | Behavior-based P2P detection method under large traffic environment |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021114844A1 (en) * | 2019-12-10 | 2021-06-17 | 华为技术有限公司 | Traffic classification method and traffic management device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiao et al. | An efficient elephant flow detection with cost-sensitive in SDN | |
| CN102271090B (en) | Transport-layer-characteristic-based traffic classification method and device | |
| Bakhshi et al. | On internet traffic classification: A two-phased machine learning approach | |
| CN101841440B (en) | Peer-to-peer network flow identification method based on support vector machine and deep packet inspection | |
| WO2018054342A1 (en) | Method and system for classifying network data stream | |
| CN101714952B (en) | Method and device for identifying traffic of access network | |
| Li et al. | MultiClassifier: A combination of DPI and ML for application-layer classification in SDN | |
| CN110011931A (en) | A kind of encryption traffic classes detection method and system | |
| CN108881028B (en) | SDN network resource scheduling method for realizing application awareness based on deep learning | |
| Areström et al. | Early online classification of encrypted traffic streams using multi-fractal features | |
| CN101645803B (en) | P2P service identification method and Internet service identification system | |
| CN102769551A (en) | Method and system for evaluating network quality and optimizing network | |
| Li et al. | Real-time P2P traffic identification | |
| Mongkolluksamee et al. | Enhancing the performance of mobile traffic identification with communication patterns | |
| CN110417729A (en) | A kind of service and application class method and system encrypting flow | |
| Le et al. | Applying big data, machine learning, and SDN/NFV for 5G early-stage traffic classification and network QoS control | |
| CN103532908B (en) | A kind of P2P protocol recognition methods based on secondary decision tree | |
| Xavier et al. | Machine learning-based early attack detection using open RAN intelligent controller | |
| Huang et al. | Application identification system for SDN QoS based on machine learning and DNS responses | |
| CN102857474A (en) | Method for identifying and classifying P2P (peer-to-peer) traffic on basis of SVM (support vector machine) technology | |
| CN113382039A (en) | Application identification method and system based on 5G mobile network flow analysis | |
| Li et al. | High performance flow feature extraction with multi-core processors | |
| Jiang et al. | AC-DC: Adaptive Ensemble Classification for Network Traffic Identification | |
| Aun et al. | A review on features' robustness in high diversity mobile traffic classifications | |
| Dong et al. | Fine grained classification of Internet multimedia traffics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130102 |
|
| WD01 | Invention patent application deemed withdrawn after publication |