Measurements and Analysis of Application-Perceived Throughput via Mobile Links

Application-perceived throughput plays a major role for the performance of networked applications and user experience and thus, for network selection decisions. To support the latter, this tutorial paper investigates the process of user-perceived throughput in GPRS and UMTS systems seen over rather small averaging intervals, based on test traffic mimicking the needs of streaming applications, and analyzes the results with aid of summary statistics. These results reveal a clear influence of the network, seen from variations and autocorrelation of applicationperceived throughput mostly on the one-second time scale and indicate that applications have to cope with significant jitter when trying to exploit the nominal throughputs. In GPRS, the promised average throughputs are not reached in downlink direction; instead, significant packet loss occurs. Furthermore, with aid of causality arguments for an equivalent bottleneck, bounds for the extra delay of the first packet sent via mobile links is derived from throughput measurements.

[1]  Markus Fiedler,et al.  Delay Performance in IP Routers , 2004 .

[2]  Sándor Molnár,et al.  TCP's role in the propagation of self-similarity in the Internet , 2003, Comput. Commun..

[3]  Markus Fiedler,et al.  The Network Utility Function : A practicable concept for assessing network impact on distributed services , 2005 .

[4]  Joachim Charzinski.  Fun Factor Dimensioning for Elastic Traffic , .

[5]  Markus Fiedler,et al.  Obtaining Reliable Bit Rate Measurements in SNMP-Managed Networks , 2002 .

[6]  Donald C. Cox,et al.  Wireless personal communications: what is it? , 1995, IEEE Wirel. Commun..

[7]  M. Fiedler,et al.  The relevance of the bufferless analysis for traffic management in telecommunication networks , 2000, 1st European Conference on Universal Multiservice Networks. ECUMN'2000 (Cat. No.00EX423).

[8]  M. Fiedler,et al.  Generic communication requirements of ITS-related mobile services as basis for seamless communications , 2005, Next Generation Internet Networks, 2005.

[9]  Zhenyu Yang,et al.  Bandwidth Measurement in Wireless Mesh Networks , 2004 .

[10]  M. Mandjes,et al.  Evaluation of 'user-oriented' and 'black-box' traffic models for link provisioning , 2005, Next Generation Internet Networks, 2005.

[11]  Douglas E. Comer,et al.  Internetworking with TCP/IP, Volume 1: Principles, Protocols, and Architectures, Fourth Edition , 2000 .

[12]  Markus Fiedler,et al.  Identification of performance degradation in IP networks using throughput statistics , 2003 .

[13]  Ilkka Norros,et al.  On the Use of Fractional Brownian Motion in the Theory of Connectionless Networks , 1995, IEEE J. Sel. Areas Commun..

[14]  Walter Willinger,et al.  On the self-similar nature of Ethernet traffic , 1993, SIGCOMM '93.

[15]  Markus Fiedler,et al.  Application of the stochastic fluid flow model for bottleneck identification and classification , 2003 .

[16]  Mikael Johansson,et al.  Traffic matrix estimation on a large IP backbone: a comparison on real data , 2004, IMC '04.

[17]  Tobias Hoßfeld,et al.  Mapping of file-sharing onto mobile environments: enhancement by UMTS , 2005, Third IEEE International Conference on Pervasive Computing and Communications Workshops.

[18]  Thomas R. Gross,et al.  Bandwidth monitoring for network-aware applications , 2001, Proceedings 10th IEEE International Symposium on High Performance Distributed Computing.

[19]  Mineo Takai,et al.  Scalable simulation of large-scale wireless networks with bounded inaccuracies , 2004, MSWiM '04.

[20]  R. D. van der Mei,et al.  Flow-level performance models for the TCP with QoS differentiation , 2002 .

[21]  Robert Tappan Morris,et al.  Variance of aggregated Web traffic , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[22]  Christian Bettstetter,et al.  GSM phase 2+ general packet radio service GPRS: Architecture, protocols, and air interface , 1999, IEEE Communications Surveys & Tutorials.

[23]  Markus Fiedler,et al.  Verification and application of a second-order scale symmetry for queueing systems , 1999 .

[24]  I. Juva,et al.  Traffic characterization for traffic engineering purposes: analysis of Funet data , 2005, Next Generation Internet Networks, 2005.