Traffic characterization of a residential wireless Internet access

• Published in: Telecommunication systems Vol. 48; no. 1-2; pp. 5 - 17
• Main Authors: Wamser, Florian, Pries, Rastin, Staehle, Dirk, Heck, Klaus, Tran-Gia, Phuoc
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01-10-2011; Springer Nature B.V
• Subjects: Analysis; Application programming interface; Artificial Intelligence; Backbone; Bandwidths; Broadband; Business; Business and Management; Computer Communication Networks; Internet; Internet access; Internet Protocol; Internet service providers; IT in Business; Measurement; Networks; Peer to peer computing; Probability Theory and Stochastic Processes; Residential; Software; Statistics; Studies; Telecommunications systems; Traffic congestion; Traffic engineering; Traffic flow; Wireless networks; Traffic measurements; Broadband wireless access; Traffic classification
• ISSN: 1018-4864; 1572-9451
• DOI: 10.1007/s11235-010-9324-0

Traffic characterization is an important means for Internet Service Providers (ISPs) to adapt and to optimize their networks to the requirements of the customers. Most network measurements are performed in the backbone of these ISPs, showing both, residential and business Internet traffic. However, the traffic characteristics of business and home users differ significantly. Therefore, we have performed measurements of home users at a broadband wireless access service provider in order to reflect only home user traffic characteristics.
In this paper, we present the results of these measurements, showing daily traffic fluctuations, flow statistics as well as application distributions. The results show a difference to backbone traffic characteristics. Furthermore, we observed a shift from web and Peer-to-Peer (P2P) file sharing traffic to streaming applications.