A joint parametric prediction model for wireless internet traffic using Hidden Markov Model
- PDF / 1,425,029 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 67 Downloads / 217 Views
A joint parametric prediction model for wireless internet traffic using Hidden Markov Model Sumit Maheshwari • Sudipta Mahapatra C. S. Kumar • K. Vasu
•
Published online: 2 December 2012 Springer Science+Business Media New York 2012
Abstract Addressing performance related issues of networks and ensuring better Quality of Service (QoS) for end-users calls for simple, tractable and realistic traffic models. The work reported here focuses on modelling the Wireless Internet traffic using realistic traffic traces collected over wireless networks and forecasting the endto-end QoS parameters for the networks. A measurement framework is set-up to collect the QoS parameters and a traffic model is designed based on Hidden Markov Model considering joint distribution of End to End Delay (E2ED or d), Inter-Packet Delay Variation (IPDV) and Packet Size. States are mapped to the four traffic classes namely conversational, streaming, interactive, and background. The model is validated by forecasting QoS parameters and the results are shown to be within the tolerance limit. Keywords Next generation wireless internet Traffic measurement Traffic modelling QoS parameters Traffic forecasting Hidden Markov Model
S. Maheshwari (&) S. Mahapatra K. Vasu Project Laboratory, Department of Electronics and Electrical Communication Engineering, Indian Institute of Technology, Kharagpur, India e-mail: [email protected] S. Mahapatra e-mail: [email protected] K. Vasu e-mail: [email protected] C. S. Kumar Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur, India e-mail: [email protected]
1 Introduction Wireless Networks are intricate systems comprising several hundreds of interconnected routers and access points (APs) on one hand and thousands of end users, running a number of applications, on the other hand. With the increasing deployment of wireless networks, the understanding of performance and behaviour of such networks has become very important. This mainly depends on the networks’ traffic pattern and characterization, and application types like VoIP, multimedia and data traffic which require different levels of Quality of Service (QoS). The main challenge of a multi-service mobile network is the integration and support of a wide variety of services such as Wireless Application Protocol (WAP), Multimedia Messaging Services (MMS), Web, e-mail etc. Thus, optimal dimensioning of these networks requires the knowledge of traffic characteristics of each service. Next Generation Wireless Internet (NGWI) will be based on wireless technologies like HSPA, Long Term Evolution (LTE) and LTE-Advanced with all the applications like Voice over IP, Video/TV over IP, Video conference, 3G Internet, gaming and other peer-to-peer social networking services running on the packet based networks. These packet based networks are converging towards an all-IP based architecture [1]. Such applications, when run on the future networks, will need characterization of traffic and optimization of the p
Data Loading...
