Research and implementation of mobile internet services identification system

The QoS management is studied to enhance the performance of mobile internet services and user experience. Therefore the various mobile internet services transferred in the network need be distinguished for providing QoS guarantees to them. This paper analyzes several Services Identification technologies, such as DPI(Deep Packet Inspection) and DFI(Deep Flow Inspection). A comprehensive design of integrating port detection, DPI and DFI are investigated to overcome the problems of low level keywords automatic acquisition in existing DPI and limited categories of identifiable services in current systems. In this paper, a Mobile Internet Services Identification System (MISIS) is proposed, and the automatic generation of string signatures techniques are used in MISIS for the extracted features from data of mobile internet services. The practical testing results demonstrate that MISIS is characterized as higher automation and accuracy in the services identification.

[1]  Andrew W. Moore,et al.  Internet traffic classification using bayesian analysis techniques , 2005, SIGMETRICS '05.

[2]  Jia Wang,et al.  Analyzing peer-to-peer traffic across large networks , 2004, IEEE/ACM Trans. Netw..

[3]  Bin Liu,et al.  P2P traffic identification by TCP flow analysis , 2006, 2006 International Workshop on Networking, Architecture, and Storages (IWNAS'06).

[4]  Konstantina Papagiannaki,et al.  Toward the Accurate Identification of Network Applications , 2005, PAM.

[5]  Xin Yang.  Improved Association Rules Algorithm for Protocol Signatures Extracting , 2010 .

[6]  T. Matsuda,et al.  Traffic Features Fit for P2P Discrimination , 2005, 6th Asia-Pacific Symposium on Information and Telecommunication Technologies.

[7]  Tomasz Imielinski,et al.  Database Mining: A Performance Perspective , 1993, IEEE Trans. Knowl. Data Eng..