Universal Mobile Telecommunications System (UMTS) is a third-generation cellular network that enables high-speed mobile Internet access. This paper evaluates the performance of the transmission control protocol (TCP) Vegas and compares its performance with TCP Reno in a UMTS environment. Bulk data transfer was considered in the simulation with varying radio channel conditions. Data losses were assumed to be only caused by the radio channel. Simulation results show that the performance of Vegas is unexpectedly worse than Reno even though the data losses were completely recovered by the UMTS radio link control layer. This has led us to conduct a detailed investigation on the behavior of Vegas in order to identify the cause of performance degradation in Vegas. The poor performance of Vegas is attributed to the UMTS radio interface characteristics which characterize by large and highly variable TCP round-trip times. The round-trip time variations activated Vegas' congestion avoidance and the sender would interpret the round-trip time variation as a sign of network congestion. Consequently, the sender shrinks its window size which reduces the transmission rate even though no TCP packet losses occur. Furthermore, a sudden increase in the instantaneous round-trip time can trigger spurious timeouts at the TCP sender using Vegas which performs unnecessary retransmissions. Spurious timeouts can lead to significant throughput reduction. Reno, on the other hand, does not show any abnormality and delivers the expected performance.
|Title of host publication||Proceedings 13th International Conference on Computer Communications and Networks, ICCCN 2004|
|Place of Publication||Piscataway, NJ, USA|
|Number of pages||6|
|Publication status||Published - 2004|
|Publisher||IEEE Computer Society|
- TCP Vegas
Lo, A., Heijenk, G., & Niemegeers, I. G. M. M. (2004). The impact of UMTS/WCDMA channel round-trip time variations on TCP Vegas throughput. In Proceedings 13th International Conference on Computer Communications and Networks, ICCCN 2004 (pp. 67-72). [10.1109/ICCCN.2004.1401590] Piscataway, NJ, USA: IEEE. https://doi.org/10.1109/ICCCN.2004.1401590