Measured performance of data transmission over cellular telephone networks

Abstract

Recent developments in mobile communication and personal computer technology have laid a new foundation for mobile computing. Performance of the data communication system as seen by an application program is a fundamental factor when communication infrastructure at the application layer is designed. This paper provides results of performance measurements of data transmission over two different cellular telephone networks, a digital GSM-network and an analogue NMT-network. Since our emphasis is on performance as seen by application programs, we use the standard TCP/IP protocols in the measurements. The performance is measured using three basic operations: establishment of a wireless dial-up connection, exchange of request-reply messages, and bulk data transfer. The external conditions under which the measurements were carried out present a normal office environment when the field strength of the cellular link is good or fairly good.

A methodology for analyzing the performance of authentication protocols

“…(2) We used two wireless network transmission capacities-9600 bits per second with a latency of 520 milliseconds to represent 2G, and 384 Kbits per second with a latency of 100 milliseconds to represent 3G network capacities [PCIA 1998;Alanko et al 1994;Liljebeg et al 1996;Metricom 2001]. (3) We varied the server capacities by speed-up factors ranging from 30 to 100.…”

Internet protocol performance over networks with wireless links

“…For connections terminating outside the CT system, an Interworking Function (IWF) is provided to interface with other networks [9]. Communication with analog telephones or modems is provided by the IWF transforming the digital voice or data frames of the CT system to analog waveforms.…”

“…To optimize use of the scarce wireless bandwidth the GSM RLP employs Selective Repeat ARQ with 6 sequence numbers in the range 0; 61 , instead of the simpler Go-Back-N. This RLP reduces the average bit error rate to 10 ,8 at the expense of variable throughput and delivery delays due to retransmissions [9]. This delay variability is on top of the long delays caused by the physical layer error recovery scheme that employs bit interleaving across multiple TDMA frame slots, regardless of RLP frame boundaries.…”

“…CT systems offer non-transparent RLPs that enhance link reliability [2,9,10] with this exact goal in mind. Another approach, applicable to both WLANs and CT systems, is adding some link layer functionality to IP, to take care of local recovery [23].…”

Mobile computing based on GSM: The Mowgli approach

“…Hence, even minor disturbances in connections usually result in failures at the application level as explained in Kojo et al (1994) and in Alanko et al (1994).…”